© 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. 21-GEMMASCOPE-RES-16K
    11. 15328
    Prev
    Next
    INDEX
    Explanations

    names of race car drivers and terms related to motorsport

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.70
    elemField
    -0.61
    rungsseite
    -0.61
     pê
    -0.56
    strix
    -0.56
    iligung
    -0.55
     tỏ
    -0.55
     pinulongan
    -0.54
    QUIR
    -0.54
    contentLoaded
    -0.52
    POSITIVE LOGITS
    TestTools
    0.59
     Circuit
    0.51
    protoimpl
    0.51
    jabat
    0.48
    θεί
    0.48
    耐久
    0.47
    évaluateur
    0.46
    copia
    0.46
    ężczy
    0.46
     pavimento
    0.45
    Activations Density 0.109%

    No Known Activations