© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11586
    Prev
    Next
    INDEX
    Explanations

    references to HTML classes and attributes in code snippets

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

    Code, math, or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    HTML and units (mg, °C, min)

    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
     
    -0.76
    </em>
    -0.66
    </strong>
    -0.65
    ِّ
    -0.63
     fi
    -0.60
     factor
    -0.57
    FACTOR
    -0.54
    rahman
    -0.54
    statistic
    -0.52
    islative
    -0.52
    POSITIVE LOGITS
    <b>
    1.48
    </b>
    1.24
    </i>
    1.05
    dfrac
    1.00
     '''
    0.79
    <i>
    0.78
    '''
    0.70
    </td>
    0.70
    例文帳に追加
    0.65
     ${\
    0.63
    Activations Density 0.057%

    No Known Activations