© 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. 15-GEMMASCOPE-RES-16K
    11. 5403
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly periods and identifiers related to object creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.77
    prüche
    -0.74
     referenties
    -0.72
    tagHelperRunner
    -0.70
     nahilalakip
    -0.70
    الحياه
    -0.67
    曖昧さ回避
    -0.66
    providedIn
    -0.66
    مصادر
    -0.62
     Référence
    -0.61
    POSITIVE LOGITS
     Diſ
    0.74
    (&:
    0.64
     ſmall
    0.61
     Inſ
    0.60
    ſelf
    0.59
     étoient
    0.56
     Beſ
    0.55
     avoient
    0.55
    cedures
    0.54
    ++.
    0.53
    Activations Density 0.118%

    No Known Activations