© 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. 8912
    Prev
    Next
    INDEX
    Explanations

    mentions of significant outcomes or events in a narrative context

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

    Usernames or IDs with numbers

    np_acts-logits-general · gemini-2.0-flash

    Calculate probability, expected outcome

    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
    UIControlState
    -0.93
     Jefus
    -0.92
    ſelf
    -0.91
    ConstraintMaker
    -0.89
     Reſ
    -0.86
     poffe
    -0.86
     fhew
    -0.82
     ſtand
    -0.82
     pleaſure
    -0.82
     Anſ
    -0.82
    POSITIVE LOGITS
     Mr
    0.78
     j
    0.77
    Mr
    0.73
     Anonymous
    0.71
     k
    0.68
     m
    0.67
     z
    0.66
     anonymous
    0.65
    Anonymous
    0.65
     @
    0.64
    Activations Density 0.227%

    No Known Activations