© 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. 13641
    Prev
    Next
    INDEX
    Explanations

    patterns of character sequences and formatting in text

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

    Preceding exclamation marks or special characters

    np_acts-logits-general · gemini-2.0-flash

    exclamatory punctuation

    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
     Roskov
    -0.92
     ProtoMessage
    -0.78
     Shakspeare
    -0.77
     !!!!!
    -0.76
     ligiloj
    -0.76
     :—
    -0.75
    
    -0.75
    లాలు
    -0.75
     !!!!
    -0.74
    ⤹
    -0.74
    POSITIVE LOGITS
    !
    1.24
    ?
    0.72
    !"
    0.64
    >
    0.63
    !,
    0.61
    ,!
    0.60
    !”
    0.59
    도
    0.58
    !)
    0.58
    !'
    0.56
    Activations Density 0.123%

    No Known Activations