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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52988
    Prev
    Next
    INDEX
    Explanations

    specific file metadata and details related to programming or coding contexts

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

    letters picked

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    InitVars
    -0.76
     Efq
    -0.68
     termica
    -0.67
    featureID
    -0.67
     murale
    -0.66
    EndGlobalSection
    -0.64
     JAXBElement
    -0.61
     Vikipedi
    -0.61
    ByExample
    -0.58
    Personendaten
    -0.58
    POSITIVE LOGITS
    pulumi
    0.68
    crose
    0.64
     }}"></
    0.60
     Rica
    0.59
     Sal
    0.57
    osoever
    0.57
    RefreshLayout
    0.55
     press
    0.55
     Tur
    0.54
    DispatchToProps
    0.52
    Activations Density 1.832%

    No Known Activations