© 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. 0-GEMMASCOPE-RES-65K
    6. 9872
    Prev
    Next
    INDEX
    Explanations

    references to responsibilities or tasks associated with a role or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esModule
    -0.66
    ogia
    -0.55
    Leaks
    -0.54
     himo
    -0.54
    Hansen
    -0.54
    arsenal
    -0.53
    queness
    -0.52
    ftagPool
    -0.51
    ensa
    -0.50
     سكانية
    -0.49
    POSITIVE LOGITS
     duty
    1.02
     duties
    0.98
    duty
    0.93
     Duty
    0.82
     DUT
    0.80
    DUT
    0.79
    Duty
    0.79
     DUTY
    0.77
     Duties
    0.76
     spending
    0.68
    Activations Density 0.065%

    No Known Activations