© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10527
    Prev
    Next
    INDEX
    Explanations

    specific commenting patterns in code snippets

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

    Code-related characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and comments

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     circulación
    -0.54
     productividad
    -0.50
     dragón
    -0.50
     mascotas
    -0.49
     celebrid
    -0.47
     templado
    -0.47
     civilización
    -0.47
     imaginación
    -0.47
     popularidad
    -0.47
     niebla
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.91
    tagHelperRunner
    0.77
    GEBURTSDATUM
    0.75
    SourceChecksum
    0.73
    parsedMessage
    0.73
     كومونز
    0.72
     arşivlendi
    0.68
    EndInit
    0.67
     roleId
    0.65
     dataType
    0.65
    Activations Density 0.958%

    No Known Activations