© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8816
    Prev
    Next
    INDEX
    Explanations

    terms associated with acceptance and rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    virons
    -0.68
    Korn
    -0.65
     старости
    -0.64
     Иль
    -0.64
     Potter
    -0.63
    mingen
    -0.63
    AdapterView
    -0.62
    highly
    -0.62
     avrebbero
    -0.61
     devriez
    -0.61
    POSITIVE LOGITS
     accept
    1.83
     Accept
    1.77
     accepts
    1.73
     acceptance
    1.67
     Accepting
    1.66
     ACCEPT
    1.65
     accepting
    1.64
     Acceptance
    1.60
     accepted
    1.58
    Accept
    1.58
    Activations Density 0.081%

    No Known Activations