© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8739
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure related to TypeScript modules and functions

    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
     SwitchCompat
    -0.67
    ItemBackground
    -0.61
    !*\
    -0.61
    ftagPool
    -0.57
    ricians
    -0.57
    NameInMap
    -0.56
    HomeAsUpEnabled
    -0.56
    Chham
    -0.56
    CPtr
    -0.55
     صوتيه
    -0.54
    POSITIVE LOGITS
    TypeScript
    0.56
    typescript
    0.54
     TypeScript
    0.49
    tsx
    0.47
     femininas
    0.35
     totalidad
    0.35
     novidades
    0.35
     ámbitos
    0.34
    Gemeinde
    0.33
     perfectamente
    0.33
    Activations Density 0.433%

    No Known Activations