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. 6-GEMMASCOPE-RES-16K
    6. 5342
    Prev
    Next
    INDEX
    Explanations

    expressions related to timing or imminent action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -0.68
    migrationBuilder
    -0.66
    XMLSchema
    -0.66
    yargs
    -0.61
    Also
    -0.59
    fetchall
    -0.58
     Also
    -0.58
    Scroller
    -0.57
    Autoritní
    -0.56
    UrlEncoded
    -0.54
    POSITIVE LOGITS
     sobald
    1.14
     whenever
    1.06
    whenever
    0.94
     Whenever
    0.92
    Whenever
    0.91
     Sobald
    0.89
     Dès
    0.85
     nadat
    0.85
    Quando
    0.84
     wanneer
    0.83
    Activations Density 0.099%

    No Known Activations