© 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. 10-GEMMASCOPE-RES-16K
    11. 15405
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical peaks and distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fact
    -0.64
     so
    -0.63
    ...
    -0.62
    .........
    -0.60
    じゃ
    -0.60
    MathML
    -0.59
     was
    -0.58
    ра
    -0.57
     "
    -0.57
      
    -0.56
    POSITIVE LOGITS
     peaks
    1.63
     PEAK
    1.60
     Peaks
    1.58
     Peak
    1.58
     peak
    1.53
    Peak
    1.48
    peak
    1.34
    peaks
    1.29
     peaking
    1.25
     peaked
    1.23
    Activations Density 0.113%

    No Known Activations