Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9167
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions of inclusivity or collective sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geografi
    -0.62
    ArrowToggle
    -0.61
     horaire
    -0.60
    contentLoaded
    -0.58
    brainly
    -0.57
    ThroughAttribute
    -0.57
    Bagh
    -0.55
     disorder
    -0.54
     للاسماء
    -0.54
     Sehr
    -0.54
    POSITIVE LOGITS
    畢竟
    0.81
    毕竟
    0.77
     ведь
    0.70
    要知道
    0.68
     hey
    0.66
     what
    0.65
    ведь
    0.65
     Schließlich
    0.65
     remember
    0.63
     przecież
    0.63
    Activations Density 0.088%

    No Known Activations