© 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. 18-GEMMASCOPE-RES-16K
    11. 8393
    Prev
    Next
    INDEX
    Explanations

    operations related to network request handling and response processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and error handling

    np_acts-logits-general · gemini-2.0-flash

    results and error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.59
     NSCoder
    -0.57
    طلحات
    -0.56
    #
    -0.54
    LookAnd
    -0.54
    醐
    -0.53
    UnknownFields
    -0.53
    RTCK
    -0.52
    iastes
    -0.52
     pomen
    -0.52
    POSITIVE LOGITS
     results
    0.75
     result
    0.71
    Result
    0.69
    result
    0.66
    results
    0.65
     Résultat
    0.61
     résultats
    0.61
     outcome
    0.60
     Result
    0.60
     RESULTS
    0.59
    Activations Density 0.082%

    No Known Activations