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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10979
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodologies and statistical analysis

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

    Statistical analysis/assessment

    np_acts-logits-general · gemini-2.0-flash

    study selection and data extraction

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     BorderSide
    -0.44
     NSCoder
    -0.44
    الدراسه
    -0.44
    BagConstraints
    -0.43
    transQ
    -0.42
    الحياه
    -0.42
    onActivityResult
    -0.42
    noaa
    -0.41
    (=)
    -0.40
    InputBorder
    -0.38
    POSITIVE LOGITS
    addCriterion
    0.46
     Dispersion
    0.44
    bindingNavigator
    0.43
     dispersion
    0.42
     nahilalakip
    0.41
    
    0.41
    uronic
    0.40
     Handeln
    0.38
    Searcher
    0.37
     déjeuner
    0.36
    Activations Density 0.780%

    No Known Activations