© 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. 3489
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to medical tests and procedures

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

    Numerical data, often enclosed in parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers around thirty

    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
    InputBorder
    -0.72
    mergeFrom
    -0.57
    windowFixed
    -0.55
    Portale
    -0.55
    ngdoc
    -0.53
     beginnetje
    -0.52
    Datuak
    -0.52
     dAtA
    -0.52
    HostException
    -0.51
    RTEX
    -0.51
    POSITIVE LOGITS
     Thirty
    0.88
     thirty
    0.85
    Thirty
    0.78
     ۳۰
    0.75
    3
    0.73
     treinta
    0.68
    三十
    0.65
    thirty
    0.65
    ۳۰
    0.61
     trente
    0.59
    Activations Density 0.537%

    No Known Activations