© 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. 7-GEMMASCOPE-RES-16K
    6. 1759
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of line breaks and whitespace characters in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experience
    -0.46
     mon
    -0.46
     Erfahrung
    -0.46
     inconnu
    -0.46
    pexpr
    -0.45
    mund
    -0.45
     Experience
    -0.44
     emailAlready
    -0.43
    stre
    -0.41
     Vi
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    extAlignment
    0.74
    bootstrapcdn
    0.73
    tagHelperRunner
    0.71
    JspWriter
    0.70
    MethodManager
    0.69
    WriteBarrier
    0.67
    StandardCharsets
    0.66
    UnusedPrivate
    0.65
    <bos>
    0.65
    Activations Density 0.270%

    No Known Activations