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. 16-GEMMASCOPE-RES-16K
    6. 12967
    Prev
    Next
    INDEX
    Explanations

    references to various components of a software framework or library

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    factory pattern instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.54
    ParseException
    -0.54
    CodeAnalysis
    -0.52
    LookAnd
    -0.52
     Вікі
    -0.52
    strconv
    -0.51
    <()>
    -0.49
     legales
    -0.49
    ToMany
    -0.48
     MotionEvent
    -0.48
    POSITIVE LOGITS
     functioning
    0.70
    ToUse
    0.68
     services
    0.64
     useAppContext
    0.63
     functional
    0.61
     toimi
    0.60
    backends
    0.59
     Siamese
    0.58
    functioning
    0.57
    ⓧ
    0.56
    Activations Density 0.325%

    No Known Activations