© 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. 20-GEMMASCOPE-RES-16K
    11. 1012
    Prev
    Next
    INDEX
    Explanations

    terms related to policy interventions and their effectiveness

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

    words related to taking action or proposing solutions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    solution-oriented, prescriptive language describing concrete actions or measures to remedy, mitigate, or address problems

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    language proposing solutions, remedies, or actions to address problems.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    nezeu
    -0.44
     bedroom
    -0.41
     disambiguazione
    -0.41
    lihatan
    -0.39
    ancers
    -0.39
    دانشنامهٔ
    -0.38
     kohdetta
    -0.38
     setSelected
    -0.37
     CONDUIT
    -0.37
    URLException
    -0.37
    POSITIVE LOGITS
     Maßnahmen
    0.74
     remedy
    0.73
     remedies
    0.72
     solutions
    0.68
    RenderAtEndOf
    0.66
     Remedy
    0.65
    maßnahmen
    0.65
    solutions
    0.64
     Remedies
    0.62
    solution
    0.60
    Activations Density 0.280%

    No Known Activations