© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    medical qualifications and specialties

    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
    elemField
    -0.48
    expandindo
    -0.47
     noDo
    -0.45
    -------------</
    -0.43
    riezmann
    -0.42
     defaultstate
    -0.42
    الحياه
    -0.42
    цездатний
    -0.41
     transfieras
    -0.40
    :✨
    -0.40
    POSITIVE LOGITS
     Internal
    1.02
     internal
    0.95
    Internal
    0.87
     INTERNAL
    0.81
    internal
    0.81
    INTERNAL
    0.73
     Intern
    0.68
     intern
    0.66
     internally
    0.65
     nephro
    0.63
    Activations Density 0.588%

    No Known Activations