© 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. 25-GEMMASCOPE-RES-16K
    11. 15783
    Prev
    Next
    INDEX
    Explanations

    conversational elements and expressions in a casual dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.52
     referenties
    -0.48
    "])
    -0.47
    StoreMessageInfo
    -0.43
     समीक्षाओं
    -0.43
    \}\\
    -0.41
    protoimpl
    -0.40
    arpa
    -0.40
     становника
    -0.40
    CodedInputStream
    -0.40
    POSITIVE LOGITS
     congrats
    0.74
    Congrats
    0.68
    congrats
    0.65
     congratulations
    0.64
     Congrats
    0.61
    Congratulations
    0.60
    congratulations
    0.58
     Congratulations
    0.52
     sounds
    0.48
    Sounds
    0.47
    Activations Density 0.221%

    No Known Activations