© 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. 35-GEMMASCOPE-RES-16K
    11. 7828
    Prev
    Next
    INDEX
    Explanations

    sections of text formatted as lists or containing structured data

    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
     BoxFit
    -0.71
    verifyException
    -0.68
    GEBURTS
    -0.66
     MainAxisSize
    -0.65
     BorderSide
    -0.65
    IsMutable
    -0.64
    principalColumn
    -0.63
    Parcelize
    -0.60
     Paglinawan
    -0.59
    oredCriteria
    -0.59
    POSITIVE LOGITS
        
    0.56
    0
    0.53
    0.43
     particulières
    0.40
     particulière
    0.40
    <h2>
    0.37
    Weather
    0.37
    ↵↵↵↵↵
    0.37
    ing
    0.34
     Económica
    0.34
    Activations Density 0.506%

    No Known Activations