© 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. 5696
    Prev
    Next
    INDEX
    Explanations

    references to organizations and associations

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

    Company or organization establishment

    np_acts-logits-general · gemini-2.0-flash

    founding and establishing organizations

    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
     مرئيه
    -0.76
     AssemblyCulture
    -0.69
     estekak
    -0.67
    AutoScaleMode
    -0.67
     دیکھیے
    -0.66
    /*
    -0.62
    ніципалі
    -0.59
    IntoConstraints
    -0.57
    TemporalType
    -0.57
    новниш
    -0.57
    POSITIVE LOGITS
     established
    2.21
     establishment
    2.17
     founded
    2.04
     Established
    2.04
    established
    1.97
     formed
    1.95
    Established
    1.90
     ESTABL
    1.90
     establishing
    1.89
     establish
    1.87
    Activations Density 0.694%

    No Known Activations