© 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. 4-GEMMASCOPE-RES-16K
    11. 3735
    Prev
    Next
    INDEX
    Explanations

    statistical metrics, particularly the term "mean" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.69
     arşivlendi
    -0.67
     noqa
    -0.66
    stě
    -0.63
    .."
    -0.61
    ..."
    -0.61
    才會
    -0.60
    icoot
    -0.60
     Joni
    -0.60
    yti
    -0.59
    POSITIVE LOGITS
    mean
    2.55
     Mean
    2.46
     mean
    2.40
    Mean
    2.29
    MEAN
    2.18
     MEAN
    2.13
    平均
    1.06
     bedeuten
    0.87
    average
    0.86
     average
    0.86
    Activations Density 0.115%

    No Known Activations