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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 25271
    Prev
    Next
    INDEX
    Explanations

    specific sequences of mathematical or programming symbols and syntax in the text

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

    parentheses with numbers/units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }>;
    -0.40
     />);
    -0.33
    })]
    -0.33
     }}$}
    -0.33
    UpInside
    -0.32
     />;
    -0.31
    STOR
    -0.30
     "'");
    -0.29
    ']));
    -0.29
    __":
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.91
    󠁴
    0.80
    oredCriteria
    0.64
     Signalez
    0.63
    Personendaten
    0.61
    CPtr
    0.60
    TintMode
    0.59
    utives
    0.58
    intios
    0.56
    windowFixed
    0.54
    Activations Density 0.217%

    No Known Activations