© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10943
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic or scholarly writing that discusses theoretical concepts, methods, or analysis in technical fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    rhetorical and organizational phrases in academic prose that signal motivation, aims, significance/usefulness, generality, and contrasts or comparisons between approaches.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    language indicating research significance, motivation, or usefulness in academic mathematical and statistical texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.50
     Chromat
    -0.50
     camped
    -0.48
    copg
    -0.47
     Capsule
    -0.46
     tetrach
    -0.46
     camping
    -0.46
    Plo
    -0.45
     Propor
    -0.45
     Estim
    -0.45
    POSITIVE LOGITS
    发表于
    0.48
     Gegenstand
    0.45
     compless
    0.44
     Bewußt
    0.43
     Anwendungs
    0.42
     abstrato
    0.41
     complexity
    0.40
     problem
    0.40
     naturen
    0.40
     Schriften
    0.40
    Activations Density 1.626%

    No Known Activations