Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6929
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and numerical analyses

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

    29-30, 28-30, 26-30

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.15
     queſta
    -0.79
     ſch
    -0.79
     vooz
    -0.74
    المناصب
    -0.73
    bootstrapcdn
    -0.72
    majánló
    -0.72
     Geſch
    -0.72
     incrí
    -0.71
    nodoc
    -0.70
    POSITIVE LOGITS
    /
    0.31
    ep
    0.31
    bl
    0.29
    2
    0.28
    bio
    0.28
    V
    0.28
     Ark
    0.28
     при
    0.27
     interim
    0.27
    5
    0.27
    Activations Density 0.194%

    No Known Activations