Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12444
    Prev
    Next
    INDEX
    Explanations

    conditional statements and associated logical operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.78
    rungsseite
    -0.67
     समीक्षाओं
    -0.67
    RegressionTest
    -0.65
    Jeografia
    -0.59
    WebElementEntity
    -0.59
    findpost
    -0.59
     Paglinawan
    -0.58
    aly
    -0.57
     CWE
    -0.56
    POSITIVE LOGITS
     Norwich
    0.77
     Wilber
    0.65
     Brenner
    0.63
     Boris
    0.62
     glacier
    0.61
     Lambert
    0.60
    viii
    0.60
     Lili
    0.59
     Bred
    0.58
     NCT
    0.58
    Activations Density 0.672%

    No Known Activations