© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    quantitative changes and measurements, particularly related to biological or experimental contexts

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

    upward or downward movement

    np_acts-logits-general · gemini-2.0-flash

    amount or level changes

    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
    Hochspringen
    -0.59
     مرئيه
    -0.53
    strcat
    -0.41
    dients
    -0.41
     AssemblyTitle
    -0.41
    InMillis
    -0.41
    TypedDataSet
    -0.41
     متعلقه
    -0.40
    wohl
    -0.40
     المعيارى
    -0.40
    POSITIVE LOGITS
    เหลือ
    0.88
    至
    0.85
    到
    0.81
     down
    0.80
     menjadi
    0.79
     xuống
    0.78
     до
    0.78
    resave
    0.74
     upto
    0.74
     lên
    0.71
    Activations Density 0.375%

    No Known Activations