Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12735
    Prev
    Next
    INDEX
    Explanations

    terminology related to programming concepts, specifically focusing on data structures, classes, and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.63
     cerevisiae
    -0.55
    GHIJKLM
    -0.53
    ahin
    -0.53
    angor
    -0.51
     onPostExecute
    -0.51
     joindre
    -0.50
     necessários
    -0.50
    cobra
    -0.50
     ""],
    -0.50
    POSITIVE LOGITS
    NUMX
    0.64
    Хьажоргаш
    0.62
     Egli
    0.60
     Dage
    0.59
    getDescriptor
    0.57
     Efq
    0.57
    ]")]
    0.56
    libft
    0.56
    Diweddarwch
    0.55
     Pues
    0.54
    Activations Density 0.693%

    No Known Activations