© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3674
    Prev
    Next
    INDEX
    Explanations

    features and specifications of vehicles, particularly focusing on luxury and performance details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical specifications and detailed feature descriptions in product or vehicle listings.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sesuatu
    -0.49
     verbs
    -0.44
     irgende
    -0.43
     valami
    -0.42
    何か
    -0.41
    posób
    -0.41
     Meksiku
    -0.41
    selben
    -0.41
     combustível
    -0.41
    parsedMessage
    -0.40
    POSITIVE LOGITS
     abundant
    0.71
     plenty
    0.70
     ample
    0.70
     plentiful
    0.69
     numerous
    0.59
    plenty
    0.59
     copious
    0.59
     extensive
    0.55
     bright
    0.55
     thick
    0.55
    Activations Density 0.316%

    No Known Activations