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. 22-GEMMASCOPE-RES-16K
    6. 13895
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts in a detailed manner

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

    "and" followed by a positive effect

    np_acts-logits-general · gemini-2.0-flash

    facilitating positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viited
    -0.66
    GEBURTSDATUM
    -0.65
    migrationBuilder
    -0.62
    HtmlAttribute
    -0.60
    EDEFAULT
    -0.59
    Искәрмәләр
    -0.58
     esternos
    -0.55
     кӀ
    -0.54
    tvguidetime
    -0.53
    dafx
    -0.50
    POSITIVE LOGITS
     allows
    1.78
     enables
    1.77
     helps
    1.72
     Allows
    1.52
    Allows
    1.50
     enable
    1.46
     gives
    1.46
     allow
    1.46
     prevents
    1.45
    helps
    1.45
    Activations Density 0.426%

    No Known Activations