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. 7-GEMMASCOPE-RES-16K
    6. 5952
    Prev
    Next
    INDEX
    Explanations

    functions or methods related to starting processes or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.77
     judiciaire
    -0.71
     scolas
    -0.71
    }\]
    -0.70
    ONYMOUS
    -0.69
     objs
    -0.67
    <h6>
    -0.66
    ;'>
    -0.64
    .$,
    -0.61
     récla
    -0.59
    POSITIVE LOGITS
    START
    1.42
    Start
    1.37
     START
    1.34
    start
    1.33
     Start
    1.33
    getStart
    1.30
     getStart
    1.17
     start
    1.14
     Begin
    1.05
     onStart
    0.99
    Activations Density 0.052%

    No Known Activations