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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15154
    Prev
    Next
    INDEX
    Explanations

    structural elements and relationships within technical or data-driven contexts

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

    before technical terms

    np_acts-logits-general · gemini-2.0-flash

    measurement and process completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoeddwyd
    -0.60
    ➟
    -0.60
    يكب
    -0.59
    帖最后由
    -0.58
    ThroughAttribute
    -0.57
    :✨
    -0.57
    IntoConstraints
    -0.55
     HttpNotFound
    -0.55
    Personendaten
    -0.54
    LookAnd
    -0.54
    POSITIVE LOGITS
     ting
    0.31
     practitioners
    0.31
     imported
    0.30
     Scheiben
    0.30
     bolsillos
    0.30
    nadores
    0.29
     backed
    0.29
     Quelles
    0.29
     tør
    0.29
     kur
    0.29
    Activations Density 1.338%

    No Known Activations