© 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. 24-GEMMASCOPE-RES-16K
    6. 5784
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to quantities in a variety of contexts

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

    Prepositions introducing locations

    np_acts-logits-general · gemini-2.0-flash

    chokes, Brick, 4th

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.76
    ItemBackground
    -0.73
     autorytatywna
    -0.70
     ویکی‌پدی
    -0.68
     HasFactory
    -0.63
    httphttps
    -0.60
    AndEndTag
    -0.60
     يتيمه
    -0.60
     ProtoMessage
    -0.59
     endwhile
    -0.59
    POSITIVE LOGITS
    Every
    0.39
    [toxicity=0]
    0.39
    PE
    0.37
    od
    0.37
      
    0.36
    Dear
    0.36
     Ru
    0.35
    M
    0.35
    Ru
    0.35
    \!\
    0.35
    Activations Density 0.167%

    No Known Activations