© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2644
    Prev
    Next
    INDEX
    Explanations

    references to action and adventure themes in video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.69
     kasarigan
    -0.68
    RuleContext
    -0.66
    tonode
    -0.65
     resourceCulture
    -0.64
    +#+
    -0.63
    addCriterion
    -0.62
     AttributeSet
    -0.56
     queſta
    -0.55
     Verſ
    -0.55
    POSITIVE LOGITS
    OGND
    0.39
    otras
    0.36
    dung
    0.30
     مه
    0.29
     zaj
    0.27
     Eder
    0.27
     meta
    0.27
    ↕
    0.27
     Deber
    0.27
     Ça
    0.27
    Activations Density 0.383%

    No Known Activations