© 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. 35-GEMMASCOPE-RES-16K
    6. 14423
    Prev
    Next
    INDEX
    Explanations

    iconographic elements or symbols often used in user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.67
    出版年
    -0.65
     OMIT
    -0.63
     ModelRenderer
    -0.59
    ="@+
    -0.59
     fieldNum
    -0.59
    setVerticalGroup
    -0.59
     <=",
    -0.59
    WebVitals
    -0.57
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
     fa
    0.59
    fw
    0.44
     Fawcett
    0.41
    fa
    0.39
     bigger
    0.35
    เฟ
    0.35
     times
    0.35
     parallel
    0.34
     FA
    0.34
     magic
    0.33
    Activations Density 0.179%

    No Known Activations