© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14509
    Prev
    Next
    INDEX
    Explanations

    the presence of specific formatting or structure markers in the text, such as beginning of sections or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.85
     виправивши
    -0.84
    berdayakan
    -0.77
    )");
    
    -0.76
    ValueStyle
    -0.74
    ]--;
    -0.73
     ―――――
    -0.72
    jgl
    -0.72
    хьтан
    -0.70
    ]++;
    -0.69
    POSITIVE LOGITS
    enumii
    0.71
     I
    0.48
    cupertino
    0.48
    thin
    0.48
    ...
    0.48
     direct
    0.47
    ish
    0.46
    AxisAlignment
    0.44
    Thin
    0.43
    itness
    0.43
    Activations Density 0.004%

    No Known Activations