© 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. 19-GEMMASCOPE-RES-16K
    11. 2745
    Prev
    Next
    INDEX
    Explanations

    statistics and measurements related to performance metrics and data outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɵɵelementEnd
    -0.62
    UserScript
    -0.60
    hots
    -0.56
    chting
    -0.53
    WriteTagHelper
    -0.52
    <bos>
    -0.52
    acabana
    -0.51
    lovakia
    -0.49
    testnet
    -0.49
    日閲覧
    -0.49
    POSITIVE LOGITS
     one
    0.86
     two
    0.80
     three
    0.78
     four
    0.76
     altrett
    0.75
     eight
    0.75
     yksi
    0.75
     seven
    0.75
     één
    0.73
     six
    0.72
    Activations Density 0.403%

    No Known Activations