© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14952
    Prev
    Next
    INDEX
    Explanations

    statements about differences or choices in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.67
    帖最后由
    -0.62
    PerformLayout
    -0.61
     >=",
    -0.57
    География
    -0.51
     fubject
    -0.50
     SqlParameter
    -0.50
     MessageBoxIcon
    -0.48
     ECTS
    -0.48
    foglal
    -0.47
    POSITIVE LOGITS
     candidate
    0.54
    inerja
    0.54
     vote
    0.53
     candidacy
    0.52
    :][
    0.52
    Vote
    0.52
    Unmarshaller
    0.51
    vote
    0.50
     voting
    0.49
     Vote
    0.49
    Activations Density 0.094%

    No Known Activations