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. 3-GEMMASCOPE-RES-16K
    6. 12022
    Prev
    Next
    INDEX
    Explanations

    declarations related to user interface elements and structural elements in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.69
     espirituales
    -0.65
     virtuales
    -0.56
     independientes
    -0.52
     الحره
    -0.50
    MigrationBuilder
    -0.50
    par
    -0.49
     invokingState
    -0.48
     supérieures
    -0.47
     Familienname
    -0.47
    POSITIVE LOGITS
    ^(@)
    0.74
    IBOutlet
    0.73
    ⓧ
    0.68
    enumi
    0.67
    ništ
    0.67
     Touchable
    0.67
    tanleria
    0.64
    Obrázky
    0.63
    ^(@
    0.62
    genheim
    0.61
    Activations Density 0.085%

    No Known Activations