© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15865
    Prev
    Next
    INDEX
    Explanations

    terminology related to statistical analysis, specifically median and sorting functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.48
    rrggbb
    -0.36
     cref
    -0.35
     theaters
    -0.34
     linguri
    -0.34
    üsü
    -0.33
    plasia
    -0.33
    ífonos
    -0.32
    ințe
    -0.32
    قایناق‌لار
    -0.32
    POSITIVE LOGITS
    windowFixed
    0.69
     averaging
    0.67
     averages
    0.67
     average
    0.66
     Average
    0.64
    average
    0.62
     AVERAGE
    0.60
    Average
    0.60
     averaged
    0.59
    AsUp
    0.56
    Activations Density 0.659%

    No Known Activations