© 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. 23-GEMMASCOPE-RES-16K
    11. 9538
    Prev
    Next
    INDEX
    Explanations

    phrases related to eligibility and requirements for participation in programs or criteria for classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    かえ
    -0.38
     сразу
    -0.36
     surprising
    -0.36
    外部連結
    -0.36
     אפ
    -0.36
     unexpected
    -0.35
    wechs
    -0.35
    textStyle
    -0.34
    atual
    -0.34
     Sir
    -0.34
    POSITIVE LOGITS
     nahilalakip
    0.67
     يتيمه
    0.48
    oa̍t
    0.48
     autorytatywna
    0.47
    bitkan
    0.47
    ActionCreators
    0.46
    MarshalTo
    0.45
     Autorizaciones
    0.44
    posedge
    0.44
    才行
    0.44
    Activations Density 0.721%

    No Known Activations