© 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. 21-GEMMASCOPE-RES-16K
    11. 16000
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reference to previously mentioned material or descriptions

    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
    MLLoader
    -0.45
    InitVars
    -0.42
    utives
    -0.39
    DotNetBar
    -0.38
    unique
    -0.36
    RTDA
    -0.35
    StructEnd
    -0.35
    awtextra
    -0.34
    insic
    -0.34
    pters
    -0.34
    POSITIVE LOGITS
     same
    0.75
    same
    0.65
    Same
    0.63
     Same
    0.63
    同上
    0.62
     CanadaChoose
    0.59
    同样的
    0.58
     samma
    0.57
     similar
    0.57
     aynı
    0.57
    Activations Density 0.790%

    No Known Activations