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. 12-GEMMASCOPE-RES-16K
    6. 4062
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data types

    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
    (");
    -0.63
    ***********/
    -0.56
     Arquivado
    -0.48
    _<
    -0.46
     ویکی‌پدیای
    -0.46
     woorden
    -0.46
    ;*/
    -0.45
    InvalidProtocol
    -0.45
    Appearances
    -0.44
    Initialize
    -0.43
    POSITIVE LOGITS
    protoimpl
    0.73
    MLLoader
    0.73
     Normdatei
    0.69
     مرئيه
    0.67
     EconPapers
    0.66
     BoxFit
    0.65
    EndInit
    0.65
     BoxDecoration
    0.65
     OFDb
    0.64
    astify
    0.64
    Activations Density 0.860%

    No Known Activations