© 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 - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1345
    Prev
    Next
    INDEX
    Explanations

    programming terms related to data structures and file management

    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
    TypedDataSet
    -0.62
     AssemblyTitle
    -0.57
    odil
    -0.55
    Popis
    -0.50
    ionali
    -0.50
     refined
    -0.49
    aneity
    -0.48
    AnimationsModule
    -0.48
    KommentareTeilen
    -0.48
    lismo
    -0.47
    POSITIVE LOGITS
     into
    1.18
    Into
    0.87
    into
    0.81
     Into
    0.79
     onto
    0.78
     INTO
    0.71
     ואת
    0.63
     adecuadamente
    0.61
    ให้
    0.60
     thành
    0.59
    Activations Density 0.776%

    No Known Activations