© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to Java and C++ programming languages

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

    programming language code syntax and structure, particularly Java and C++ keywords, method signatures, and structural tokens.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fmt
    -0.33
     sprend
    -0.33
    stdc
    -0.33
     led
    -0.32
     communicated
    -0.31
     escuchado
    -0.31
     obligado
    -0.31
     even
    -0.30
    velocityX
    -0.30
     conveyed
    -0.29
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
     ویکی‌پدی
    0.76
    LookAnd
    0.74
    uxxxx
    0.73
    HasAnnotation
    0.71
    MLLoader
    0.69
     autorytatywna
    0.65
     FetchType
    0.65
    ="@+
    0.63
     '\\;'
    0.63
    Activations Density 0.774%

    No Known Activations