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. 20-GEMMASCOPE-RES-131K
    6. 66784
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and related attributes

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

    numeric code followed by semicolon

    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
     CreateTagHelper
    -0.83
    RenderAtEndOf
    -0.74
    ']));
    -0.73
    })*/
    -0.71
     Vikipedi
    -0.71
    ᅠ
    -0.69
    BASEPATH
    -0.69
    ﹧
    -0.68
    ésultats
    -0.68
    ſſung
    -0.66
    POSITIVE LOGITS
    .
    0.28
    gesehen
    0.28
    LogFactory
    0.28
     actuels
    0.28
    iasaan
    0.27
    MathML
    0.27
    J
    0.27
    L
    0.26
     Viertel
    0.26
     Posteriormente
    0.26
    Activations Density 0.003%

    No Known Activations