© 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. 5233
    Prev
    Next
    INDEX
    Explanations

    dialogue marks and conversational responses

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

    Follows quotation marks or symbols

    np_acts-logits-general · gemini-2.0-flash

    quote attribution or reference markers

    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
     '\\;'
    -0.60
    RTCF
    -0.59
    новниш
    -0.56
    GTCX
    -0.52
    ")));
    
    -0.50
    )");
    
    -0.49
    featureID
    -0.49
    "):
    
    -0.48
    }));
    
    -0.48
    TintMode
    -0.47
    POSITIVE LOGITS
    hlás
    0.43
    uguetes
    0.38
    Robo
    0.38
     lilla
    0.37
    inistro
    0.36
    Източници
    0.36
     Informasi
    0.36
     Poitiers
    0.36
     كومونز
    0.36
     föres
    0.36
    Activations Density 0.057%

    No Known Activations