© 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. 11-GEMMASCOPE-RES-16K
    11. 1618
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate debate, questioning, or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.75
    DockStyle
    -0.69
    脚注の使い方
    -0.69
    msgTypes
    -0.66
    ніципалі
    -0.66
    rrggbb
    -0.65
     préférence
    -0.64
    CppCodeGen
    -0.64
    AnchorStyles
    -0.63
     ainfi
    -0.62
    POSITIVE LOGITS
     reasons
    0.67
     discussion
    0.63
     political
    0.57
     technical
    0.57
     debatable
    0.55
     debate
    0.54
     Reasons
    0.52
     discussions
    0.52
     Suff
    0.51
     debates
    0.50
    Activations Density 0.478%

    No Known Activations