© 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. 3-GEMMASCOPE-RES-16K
    6. 8095
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to specific programming components or items

    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
    Personensuche
    -0.90
     CoreData
    -0.88
     compass
    -0.81
    WireFormatLite
    -0.81
    تفصیلات
    -0.80
     Winding
    -0.76
     CUCET
    -0.76
     iveco
    -0.75
     Carrots
    -0.75
     Rosas
    -0.74
    POSITIVE LOGITS
     SL
    2.67
    SL
    2.43
     sl
    2.40
    sl
    2.22
     Sl
    2.15
    Sl
    1.93
     Sla
    1.69
    Sla
    1.45
     sla
    1.41
    slu
    1.40
    Activations Density 0.117%

    No Known Activations