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. 8215
    Prev
    Next
    INDEX
    Explanations

    relevant terms associated with management, guidance, and community engagement

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

    followed by commas, "and," or "or."

    np_acts-logits-general · gemini-2.0-flash

    analysis, tissues, fungal, energy, Africa, manage, marketing, reliable, styles, friends, stored

    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
    CodeAttribute
    -0.52
     */;
    -0.52
     pinulongan
    -0.52
    */;
    -0.50
     Autorizaciones
    -0.50
     CGRectMake
    -0.48
    Skocz
    -0.47
    GOR
    -0.47
     CORD
    -0.47
    unknownFields
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.45
     and
    0.43
     HasFactory
    0.42
     ſta
    0.40
     faſt
    0.39
     חיצוניים
    0.38
    følgelig
    0.38
     viſ
    0.36
    Життєпис
    0.36
    ſelf
    0.36
    Activations Density 0.599%

    No Known Activations