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. 4914
    Prev
    Next
    INDEX
    Explanations

    terms related to the development and refinement of mathematical or theoretical concepts

    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
     caufe
    -0.58
     zirc
    -0.58
     disambiguazione
    -0.58
    anone
    -0.57
    참고
    -0.56
    PMailer
    -0.54
     CMake
    -0.54
     Vikipedi
    -0.53
    tserrat
    -0.53
    IntoConstraints
    -0.51
    POSITIVE LOGITS
    IBOutlet
    0.56
    enumi
    0.56
     IBOutlet
    0.54
    ToScroll
    0.52
    곧
    0.52
     '>=
    0.51
    ftagPool
    0.45
    Diámetro
    0.45
    Especificación
    0.45
    putstr
    0.45
    Activations Density 0.763%

    No Known Activations