© 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. 23-GEMMASCOPE-RES-16K
    11. 11767
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and methods with varying levels of complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.79
    -
    -0.70
    ,
    -0.68
    ↵↵
    -0.68
    .
    -0.66
    ↵
    -0.63
     (
    -0.62
     -
    -0.60
     
    -0.59
    of
    -0.58
    POSITIVE LOGITS
    ^(@)
    1.24
     myſelf
    1.22
     itſelf
    1.17
     Theſe
    1.15
     Majefty
    1.15
     doubtnut
    1.14
     themſelves
    1.13
     Efq
    1.13
     ModelExpression
    1.10
     himſelf
    1.10
    Activations Density 0.043%

    No Known Activations