© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13945
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and evaluations

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

    after negations

    np_acts-logits-general · gemini-2.0-flash

    technical limitations or failure

    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
     otomatig
    -0.39
     spra
    -0.38
    Solución
    -0.34
    oredCriteria
    -0.34
     poč
    -0.34
    Попис
    -0.34
    WithIOException
    -0.34
     expedition
    -0.34
    といけない
    -0.32
     slicing
    -0.32
    POSITIVE LOGITS
    WebMethod
    0.57
    WriteLiteral
    0.54
     onPostExecute
    0.52
    पया
    0.45
    Parcelize
    0.45
    getMenuInflater
    0.42
     ویکی‌پدیا
    0.42
    ="@+
    0.41
    Nationalité
    0.40
    subplots
    0.40
    Activations Density 0.829%

    No Known Activations