© 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. 21-GEMMASCOPE-RES-16K
    6. 14012
    Prev
    Next
    INDEX
    Explanations

    references to specific figures and tables within a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fören
    -0.40
     Italijani
    -0.39
    fillType
    -0.37
     FetchType
    -0.36
     beginnetje
    -0.35
     lenker
    -0.35
    blij
    -0.35
    IVEREF
    -0.35
     mergeFrom
    -0.35
    endregion
    -0.35
    POSITIVE LOGITS
    fjspx
    0.57
     internals
    0.47
    ContentAsync
    0.47
    uberge
    0.45
    İstinadlar
    0.43
     Mexicana
    0.43
    ˒
    0.43
    nexpected
    0.43
     mics
    0.43
    ="@+
    0.43
    Activations Density 0.195%

    No Known Activations