© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 15368
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and functions, particularly those related to factors and divisors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bibitem
    -0.56
    writeFieldEnd
    -0.56
    EndContext
    -0.55
    SEB
    -0.53
    UnknownFieldSet
    -0.52
    ArgumentParser
    -0.51
    Sucesor
    -0.49
    Œuvres
    -0.47
    단
    -0.47
    ainya
    -0.46
    POSITIVE LOGITS
    ografija
    0.63
    блица
    0.56
    Последние
    0.55
     pinulongan
    0.54
    InputTagHelper
    0.54
     noastre
    0.53
    OrEqualTo
    0.53
    argout
    0.51
     dispozici
    0.50
    skjaer
    0.49
    Activations Density 0.561%

    No Known Activations