© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    elements related to functionality and control in technology and creativity

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

    technical or analytical language about control, quality, and optimization.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     Meksiku
    -0.67
    uxxxx
    -0.60
    Cyfarwyddwr
    -0.59
     Theſe
    -0.58
     <>",
    -0.56
     Roskov
    -0.55
     configureStore
    -0.54
     initComponents
    -0.54
     kasarigan
    -0.53
    RegressionTest
    -0.53
    POSITIVE LOGITS
     läßt
    0.33
    ⓧ
    0.28
     []:
    0.27
     Bewußt
    0.27
     Betreuung
    0.27
     besky
    0.27
    어
    0.26
     concentrate
    0.26
    &=&
    0.26
     conoc
    0.25
    Activations Density 0.292%

    No Known Activations