© 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. 22-GEMMASCOPE-RES-16K
    11. 8955
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming operations and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File paths containing "/tmp/"

    np_acts-logits-general · gemini-2.0-flash

    /tmp/ paths and temporary files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dora
    -0.61
     Acorn
    -0.61
     Acton
    -0.60
     Leah
    -0.59
     Napa
    -0.59
     Kue
    -0.58
     Furn
    -0.58
     FURN
    -0.58
     Bora
    -0.57
     Sarm
    -0.56
    POSITIVE LOGITS
     tmp
    1.38
    tmp
    1.31
    Tmp
    1.25
    tmpl
    1.00
     TMP
    0.96
     Williams
    0.83
    TMP
    0.83
     Blanche
    0.82
     Alfred
    0.80
     Lima
    0.80
    Activations Density 0.419%

    No Known Activations