© 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. 12592
    Prev
    Next
    INDEX
    Explanations

    specific biological measurements and experimental parameters

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

    before experimental results or data

    np_acts-logits-general · gemini-2.0-flash

    tested whether

    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
     aikaa
    -0.67
     visitare
    -0.60
     sabbia
    -0.60
     يتيمه
    -0.59
     appunt
    -0.58
     pagare
    -0.57
    TDS
    -0.56
     féd
    -0.56
     enfans
    -0.56
    SST
    -0.55
    POSITIVE LOGITS
     putative
    0.86
     expression
    0.82
     overexpression
    0.80
     phenotype
    0.77
     purified
    0.77
     assayed
    0.77
     assays
    0.76
     assay
    0.75
     experimentally
    0.75
     homology
    0.75
    Activations Density 6.367%

    No Known Activations