© 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. 17-GEMMASCOPE-RES-16K
    11. 10596
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements or specifications related to physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postmedia
    -0.47
     Shareholders
    -0.47
     onlyOwner
    -0.44
     Imagery
    -0.44
    Passcode
    -0.44
     SqlCommand
    -0.44
    ồm
    -0.43
    nib
    -0.42
    spr
    -0.42
    ViewFeatures
    -0.42
    POSITIVE LOGITS
     search
    1.60
     searching
    1.45
     searches
    1.38
    Finding
    1.35
     finding
    1.33
     Finding
    1.32
     Search
    1.32
    search
    1.32
     searched
    1.29
     SEARCH
    1.26
    Activations Density 0.281%

    No Known Activations