© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6764
    Prev
    Next
    INDEX
    Explanations

    PHP code structures and syntax elements related to conditional statements and loops

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

    Code snippets (often PHP)

    np_acts-logits-general · gemini-2.0-flash

    programming code and math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.84
    Personendaten
    -0.75
    aarrggbb
    -0.73
    enterOuterAlt
    -0.72
    ("")]
    
    -0.72
    findpost
    -0.72
    orghini
    -0.72
    eradish
    -0.72
    routeProvider
    -0.71
    المناصب
    -0.71
    POSITIVE LOGITS
    if
    0.50
     speaking
    0.49
     Speaking
    0.46
     accident
    0.45
    ula
    0.45
    int
    0.44
    cal
    0.44
    in
    0.43
    inafter
    0.42
    app
    0.42
    Activations Density 0.034%

    No Known Activations