© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11812
    Prev
    Next
    INDEX
    Explanations

    programming terminology related to states and effects in code structures

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

    compound words or multi-part identifiers in code (like variable names, class names, and method names composed of concatenated words).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.62
    CloseOperation
    -0.60
    帖最后由
    -0.58
     engraçadas
    -0.56
    DockStyle
    -0.54
    GEBURTSDATUM
    -0.54
    AnchorStyles
    -0.53
    下载附件
    -0.52
     AssemblyTitle
    -0.51
    EndGlobalSection
    -0.51
    POSITIVE LOGITS
    _
    0.57
     type
    0.49
    thme
    0.48
    fVar
    0.48
     metadata
    0.47
     configuration
    0.46
     item
    0.46
    ology
    0.46
    uation
    0.46
     data
    0.44
    Activations Density 0.481%

    No Known Activations