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. 21-GEMMASCOPE-RES-16K
    6. 1001
    Prev
    Next
    INDEX
    Explanations

    references to numbers, parameters, and scientific notation commonly used in mathematical and physics contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.65
    RenderAtEndOf
    -0.63
     dAtA
    -0.56
    UnknownFieldSet
    -0.55
    UrlResolution
    -0.54
    TProtocol
    -0.52
    WithIOException
    -0.52
     alphabetically
    -0.51
     Anything
    -0.51
    ▾
    -0.50
    POSITIVE LOGITS
    onViewCreated
    0.64
     olvas
    0.52
    enderror
    0.50
    leukin
    0.50
    irmish
    0.49
    __':
    
    0.48
    UIApplication
    0.48
    henswürdigkeiten
    0.47
    tabler
    0.47
     wikipagina
    0.46
    Activations Density 0.248%

    No Known Activations