© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 11004
    Prev
    Next
    INDEX
    Explanations

    references to measurements and constraints related to particle physics and the Standard Model

    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
     journey
    -0.43
    enaire
    -0.43
    jsxFileName
    -0.42
    Архівовано
    -0.42
     pack
    -0.42
     flo
    -0.41
     traffic
    -0.40
     Flow
    -0.40
     flow
    -0.39
    IntoConstraints
    -0.39
    POSITIVE LOGITS
     kasarigan
    0.78
    хьтан
    0.77
    ագրություններ
    0.71
     quæ
    0.69
     rospy
    0.69
     atheists
    0.66
     onAnimation
    0.64
    numerusform
    0.63
    Билгалдахарш
    0.63
     chastity
    0.63
    Activations Density 1.617%

    No Known Activations