© 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. 11-GEMMASCOPE-RES-16K
    11. 14123
    Prev
    Next
    INDEX
    Explanations

    specific numerical and chemical descriptions related to compositions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical, domain-specific nouns and morphemes—especially anatomical, mechanical, and chemical terms in scientific or engineering prose, often accompanied by hyphens/underscores or numeric qualifiers.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.64
    StructEnd
    -0.63
    AsUp
    -0.58
     Réponses
    -0.54
    RTLD
    -0.53
    amaged
    -0.53
    ':[
    -0.53
     Certi
    -0.52
     ✭✭
    -0.50
    >`;
    -0.49
    POSITIVE LOGITS
    parte
    0.49
    üglich
    0.48
     Motta
    0.48
    withIdentifier
    0.47
    EndContext
    0.47
    rinhos
    0.47
    InSection
    0.47
     continúas
    0.46
    GMENT
    0.46
    RegistryLite
    0.45
    Activations Density 1.390%

    No Known Activations