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. 5433
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and strings often associated with identifiers or codes

    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
    DeleteBehavior
    -0.91
     насељу
    -0.82
    ViewFeatures
    -0.79
    abestanden
    -0.77
    InjectAttribute
    -0.77
    AutoresizingMask
    -0.76
    ContentAsync
    -0.74
     незавершена
    -0.73
    Autoritní
    -0.71
     дописавши
    -0.68
    POSITIVE LOGITS
     ब्रेकडाउन
    0.48
    şit
    0.47
    janja
    0.47
    ODY
    0.47
    StoreMessageInfo
    0.46
    aney
    0.46
    참고
    0.45
    ại
    0.44
    l
    0.44
    mbor
    0.44
    Activations Density 0.015%

    No Known Activations