© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97155
    Prev
    Next
    INDEX
    Explanations

    occurrences of titles in a structured format, likely representing JSON or similar data formats

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

    title key in data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hybrid
    -0.44
     bArr
    -0.42
     depositphotos
    -0.42
    Numerade
    -0.41
     Armies
    -0.40
    adpleegd
    -0.40
     seaman
    -0.40
     monk
    -0.40
     mechanic
    -0.40
    gungen
    -0.39
    POSITIVE LOGITS
    title
    0.93
     title
    0.90
     getTitle
    0.80
    Title
    0.77
     Title
    0.77
     titles
    0.75
    getTitle
    0.73
     título
    0.70
    titles
    0.70
     TITLE
    0.69
    Activations Density 0.010%

    No Known Activations