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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12573
    Prev
    Next
    INDEX
    Explanations

    references to authors or collaborators in research papers

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

    "et al"

    np_acts-logits-general · gemini-2.0-flash

    et al. citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     придется
    -0.39
    TokenNameRPAREN
    -0.39
    ruzione
    -0.37
     favor
    -0.36
    SafeAreaView
    -0.35
     Axial
    -0.32
     quam
    -0.31
    transaction
    -0.31
    тент
    -0.30
    ほど
    -0.30
    POSITIVE LOGITS
     others
    0.88
     cetera
    0.82
    others
    0.79
    RenderAtEndOf
    0.73
    Others
    0.69
     autres
    0.68
    rungsseite
    0.66
    etc
    0.66
    IsMutable
    0.66
     OTHERS
    0.66
    Activations Density 0.262%

    No Known Activations