Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116892
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting elements that indicate unusual text

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

    その followed by specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.62
    styleType
    -0.55
    показания
    -0.54
    AsUp
    -0.53
     Nox
    -0.52
    Nox
    -0.50
     Wix
    -0.50
     Normdatei
    -0.50
     Diony
    -0.49
     fortification
    -0.49
    POSITIVE LOGITS
    ​
    0.79
    .​
    0.78
     ​
    0.77
    ,​
    0.73
    }$​
    0.69
    存于互联网档案馆
    0.69
    :​
    0.66
    $​
    0.66
    )​
    0.65
    ;
    
    
    0.50
    Activations Density 0.009%

    No Known Activations