© 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. 4-GEMMASCOPE-RES-16K
    6. 1690
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appunto
    -0.70
     '\\;'
    -0.67
    存于互联网档案馆
    -0.65
     stihl
    -0.60
    flich
    -0.59
    مراجع
    -0.58
     comerciais
    -0.56
     algun
    -0.56
    setVerticalGroup
    -0.55
     Dostupné
    -0.55
    POSITIVE LOGITS
    invokeLater
    0.61
    superuser
    0.61
    yczny
    0.58
    QRect
    0.58
     mostrarán
    0.58
    ResponseCode
    0.57
     Catto
    0.57
    afficheront
    0.57
     sum
    0.53
    Παραπομπές
    0.51
    Activations Density 1.323%

    No Known Activations