© 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. 24-GEMMASCOPE-RES-16K
    6. 1611
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to mathematical or scientific equations

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

    Code, math, or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    variable names with primes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <sup>
    -0.61
    ((
    -0.59
    (-
    -0.59
     }\
    -0.57
    (_
    -0.57
    </i>
    -0.57
     (_
    -0.55
     (-
    -0.55
     ((
    -0.55
    sian
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.73
     виправивши
    0.72
    ніципалі
    0.72
     BoxFit
    0.70
    HtmlAttribute
    0.65
    IBarButtonItem
    0.64
    Portail
    0.64
    AccessorTable
    0.64
    榄
    0.63
    XmlAccessType
    0.63
    Activations Density 0.007%

    No Known Activations