© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4774
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation and phrases indicating opinion or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     avanzado
    -0.45
     abandonné
    -0.44
    ไม้
    -0.38
     jupe
    -0.38
     pondok
    -0.37
     refusé
    -0.36
    níků
    -0.36
     indépend
    -0.36
     indépendant
    -0.36
    Remarque
    -0.35
    POSITIVE LOGITS
    存于互联网档案馆
    0.73
    abestanden
    0.68
    Bibliograf
    0.65
     صوتيه
    0.59
    issory
    0.58
     tartalomajánló
    0.56
    ">)</
    0.56
    NameInMap
    0.56
     nahilalakip
    0.56
    Tembelea
    0.55
    Activations Density 0.386%

    No Known Activations