© 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. 38-GEMMASCOPE-RES-16K
    6. 10142
    Prev
    Next
    INDEX
    Explanations

    references to devices and their characteristics, particularly in contexts relating to visibility and optical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.59
    UnifiedTopology
    -0.49
    الدراسه
    -0.49
    Biographie
    -0.45
     unknownFields
    -0.44
     informée
    -0.43
     kasarigan
    -0.42
    esistenza
    -0.42
    Xna
    -0.42
    DatabaseError
    -0.42
    POSITIVE LOGITS
     visible
    2.19
     obvious
    1.93
     noticeable
    1.88
    visible
    1.79
     Visible
    1.77
    obvious
    1.73
     evident
    1.70
     visibly
    1.66
     conspicuous
    1.63
     visibles
    1.61
    Activations Density 0.830%

    No Known Activations