© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2291
    Prev
    Next
    INDEX
    Explanations

    elements related to guidelines, authorities, and regulations

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

    references to organizational acronyms and specific organizations (like ACPO, Space Federation).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    UrlResolution
    -0.67
    principalTable
    -0.65
    دانشنامهٔ
    -0.61
     otomatig
    -0.60
     censiti
    -0.59
     ExecuteAsync
    -0.55
     BoxFit
    -0.54
    хьтан
    -0.54
    Попис
    -0.53
     ffilmiau
    -0.51
    POSITIVE LOGITS
    CreateMap
    0.41
     permit
    0.35
     approval
    0.34
     שמע
    0.32
     help
    0.31
     mergeFrom
    0.31
     helping
    0.30
    AUTHENT
    0.30
    maxlen
    0.29
     vinci
    0.28
    Activations Density 0.424%

    No Known Activations