© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12336
    Prev
    Next
    INDEX
    Explanations

    verbs related to running or movement

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

    "run" and its various forms

    np_acts-logits-general · gemini-2.0-flash

    run out, into, off, behind

    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
    "}")
    -0.69
     Poon
    -0.60
    égard
    -0.58
     cref
    -0.56
    theless
    -0.55
     offerts
    -0.55
    templateUrl
    -0.53
    .)}
    -0.53
    Géographie
    -0.53
    enumi
    -0.53
    POSITIVE LOGITS
     runs
    1.07
     Runs
    1.07
     Run
    1.03
     run
    0.99
    Runs
    0.98
     errands
    0.97
    runs
    0.96
     RUN
    0.96
    Run
    0.96
     ran
    0.93
    Activations Density 0.086%

    No Known Activations