Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 701
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding-related keywords

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

    Text or titles followed by section headings

    np_acts-logits-general · gemini-2.0-flash

    citizenship, chronic aging, court cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.36
     a
    -1.26
     the
    -1.11
     “
    -1.10
     in
    -1.09
     "
    -1.07
     ‘
    -1.00
     '
    -0.96
     for
    -0.95
     an
    -0.91
    POSITIVE LOGITS
    IntoConstraints
    1.63
    تقاوى
    1.42
     متعلقه
    1.38
    DoubleQuotes
    1.35
    IsMutable
    1.34
    DockStyle
    1.34
    GEBURTSDATUM
    1.32
     itſelf
    1.32
    RectangleBorder
    1.30
    WebVitals
    1.29
    Activations Density 0.791%

    No Known Activations