© 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. 20-GEMMASCOPE-RES-16K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    numerical data and their associated contextual elements

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

    Academic tests, questions, or items

    np_acts-logits-general · gemini-2.0-flash

    exam marks test items

    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
    insics
    -0.47
    orited
    -0.40
    adpleegd
    -0.38
    VersionUID
    -0.38
    LookAnd
    -0.38
     Skip
    -0.37
    liceerd
    -0.37
    $_['
    -0.36
     skip
    -0.36
     initComponents
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.46
    Билгалдахарш
    0.45
    épreuve
    0.43
    
    0.39
    AndEndTag
    0.39
    iedenen
    0.38
    MathML
    0.38
     Exactos
    0.38
     ब्रेकडाउन
    0.38
     autorytatywna
    0.37
    Activations Density 0.085%

    No Known Activations