Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1316
    Prev
    Next
    INDEX
    Explanations

    code segments related to JavaScript object manipulation and condition handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >(
    -0.66
    єра
    -0.59
    rasında
    -0.59
     zapo
    -0.58
    NewUrlParser
    -0.58
    >−
    -0.57
    <>(
    -0.57
    ottes
    -0.56
    δή
    -0.55
    UMBIA
    -0.55
    POSITIVE LOGITS
    PerformLayout
    0.93
     مشين
    0.89
    ContentAsync
    0.71
     Audiodateien
    0.70
     AssemblyProduct
    0.70
    IsMutable
    0.69
    Koordinaten
    0.67
     colic
    0.63
    enumi
    0.62
     nakalista
    0.61
    Activations Density 0.030%

    No Known Activations