© 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. 22-GEMMASCOPE-RES-16K
    11. 5919
    Prev
    Next
    INDEX
    Explanations

    identifiers and structures related to object-oriented programming concepts, particularly classes, methods, and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -0.33
     péné
    -0.33
    ńcu
    -0.32
    ardless
    -0.31
     committees
    -0.31
     initComponents
    -0.30
    itinéraire
    -0.30
     appré
    -0.29
     recuer
    -0.29
     solo
    -0.29
    POSITIVE LOGITS
     propOrder
    0.92
    DockStyle
    0.74
    تقاوى
    0.71
     kaarangay
    0.65
    Personendaten
    0.64
    oa̍t
    0.63
     ویکی‌پدی
    0.63
    новништво
    0.61
     nakalista
    0.61
    FailureListener
    0.60
    Activations Density 0.181%

    No Known Activations