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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 12125
    Prev
    Next
    INDEX
    Explanations

    instances of error handling statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    তথ্যসূত্র
    -0.68
    PerformLayout
    -0.65
     صوتيه
    -0.61
    intios
    -0.60
    ----</
    -0.59
    CppCodeGen
    -0.58
    Rohy
    -0.57
     Woodruff
    -0.57
    olson
    -0.57
     فريبيس
    -0.56
    POSITIVE LOGITS
    catch
    0.81
    Portály
    0.70
    帖最后由
    0.67
    Catch
    0.66
    catchError
    0.66
     catch
    0.63
     الحره
    0.62
     дописавши
    0.62
     CATCH
    0.61
    sedown
    0.58
    Activations Density 0.007%

    No Known Activations