© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1822
    Prev
    Next
    INDEX
    Explanations

    terms related to technical coding structures and operations

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

    technical code-related syntax and programming terminology.

    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
     gustó
    -0.49
    writeFieldEnd
    -0.48
     světě
    -0.47
     podéis
    -0.46
     hicimos
    -0.45
     hacemos
    -0.40
     Kommune
    -0.40
    rxjs
    -0.40
    làm
    -0.40
     Mehrheit
    -0.40
    POSITIVE LOGITS
     T
    0.86
    T
    0.73
     TT
    0.69
    getT
    0.68
     Tc
    0.67
    tuesday
    0.67
     t
    0.66
     Tl
    0.65
     Tey
    0.63
     Tb
    0.62
    Activations Density 1.163%

    No Known Activations