© 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. 21-GEMMASCOPE-RES-16K
    11. 2719
    Prev
    Next
    INDEX
    Explanations

    quantitative measures related to evaluation and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.69
    adaptiveStyles
    -0.59
     szóci
    -0.59
     ushort
    -0.57
     shenanigans
    -0.55
    [@
    -0.54
    órc
    -0.54
    oredCriteria
    -0.54
    FormTagHelper
    -0.53
    ритори
    -0.52
    POSITIVE LOGITS
     things
    0.78
     outcomes
    0.70
     aquilo
    0.70
     something
    0.68
     outcome
    0.66
     situations
    0.64
    things
    0.64
    trui
    0.63
     circonstances
    0.63
     actions
    0.62
    Activations Density 0.581%

    No Known Activations