© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8083
    Prev
    Next
    INDEX
    Explanations

    a variety of punctuation and symbols used in structured data or text formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     مشين
    -0.96
    Personendaten
    -0.84
    invokeLater
    -0.81
     صوتيه
    -0.77
     nahilalakip
    -0.72
    GEBURTSDATUM
    -0.72
     autorytatywna
    -0.71
    runApp
    -0.70
    RTEE
    -0.68
    setVerticalGroup
    -0.68
    POSITIVE LOGITS
    PYX
    0.65
    lamabad
    0.58
     solas
    0.51
    tern
    0.47
    UMBIA
    0.47
    Così
    0.44
    ниях
    0.44
     BY
    0.43
     AL
    0.43
    ellees
    0.43
    Activations Density 0.270%

    No Known Activations