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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11369
    Prev
    Next
    INDEX
    Explanations

    elements related to class definitions and component structures in programming, particularly in JavaScript or TypeScript context

    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
    __':
    
    -0.66
    AddTagHelper
    -0.59
    UrlResolution
    -0.57
     Pickles
    -0.56
    VIAF
    -0.56
     Vars
    -0.56
     lief
    -0.56
     IMPAC
    -0.55
     Himo
    -0.54
    udessa
    -0.53
    POSITIVE LOGITS
    memberof
    0.67
    MemoryWarning
    0.63
     sanitaires
    0.63
    UnitTesting
    0.62
    providedIn
    0.61
     IActionResult
    0.59
     مشين
    0.58
     BoxFit
    0.57
    styleUrls
    0.57
    onChanged
    0.55
    Activations Density 0.050%

    No Known Activations