© 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. 7-GEMMASCOPE-RES-16K
    11. 15917
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opportunities or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mourut
    -0.46
     trouw
    -0.41
     receitas
    -0.40
    sigkeit
    -0.40
     dipendenti
    -0.39
     houden
    -0.38
     gesteld
    -0.38
    simpleType
    -0.38
     للاسماء
    -0.38
     financieras
    -0.38
    POSITIVE LOGITS
     chance
    2.36
    chance
    2.11
    Chance
    1.98
     Chance
    1.96
     CHANCE
    1.78
     chances
    1.54
     opportunity
    1.38
     шанс
    1.38
     Chances
    1.30
     oportunidad
    1.27
    Activations Density 0.112%

    No Known Activations