© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10177
    Prev
    Next
    INDEX
    Explanations

    details related to vehicle recalls and maintenance issues

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

    Action of repairing, removing, or replacing items

    np_acts-logits-general · gemini-2.0-flash

    removed or replaced

    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
     giapp
    -0.61
     esforço
    -0.60
     vált
    -0.60
     pescoço
    -0.59
     händer
    -0.59
     evolução
    -0.58
     esfuer
    -0.58
     épaules
    -0.57
     avoient
    -0.57
     verspre
    -0.56
    POSITIVE LOGITS
    ThroughAttribute
    0.69
     replace
    0.69
     install
    0.68
     repa
    0.67
    oa̍t
    0.65
     externi
    0.64
     reti
    0.64
     autorytatywna
    0.64
     remove
    0.63
     repla
    0.63
    Activations Density 0.224%

    No Known Activations