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. 9407
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and elements, particularly related to data processing and system definitions

    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
    LookAnd
    -1.03
    Personensuche
    -0.66
    windowFixed
    -0.65
    évaluateur
    -0.62
     AssemblyCulture
    -0.61
    setViewName
    -0.56
    afficheront
    -0.56
    تقاوى
    -0.55
     himo
    -0.54
    enterOuterAlt
    -0.53
    POSITIVE LOGITS
    Hentet
    0.76
     الحره
    0.71
    FormState
    0.65
    ształ
    0.57
     skydd
    0.55
     EventArgs
    0.51
    odeficiency
    0.51
    ęć
    0.51
    yaszt
    0.50
    DataAnnotations
    0.50
    Activations Density 0.993%

    No Known Activations