© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9141
    Prev
    Next
    INDEX
    Explanations

    references to legal or political regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sometimes
    -0.39
     må
    -0.34
     most
    -0.34
     TEE
    -0.33
     occasionally
    -0.33
    sometimes
    -0.33
     Straight
    -0.32
    HEK
    -0.32
    とき
    -0.32
     maybe
    -0.32
    POSITIVE LOGITS
     quelconque
    0.87
     quelcon
    0.82
     any
    0.77
    有任何
    0.77
    任何
    0.75
    任何人
    0.72
    kolwiek
    0.70
     qualquer
    0.66
     kasarigan
    0.66
    ValueStyle
    0.65
    Activations Density 0.413%

    No Known Activations