© 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. 40-GEMMASCOPE-RES-16K
    11. 5369
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to regulations and court opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RESULTS
    -0.63
     THIS
    -0.63
     OTHER
    -0.60
     THOSE
    -0.58
     THESE
    -0.58
     INFORMATION
    -0.58
     CURRENT
    -0.58
     FOLLOWING
    -0.57
     SECOND
    -0.57
     THREE
    -0.57
    POSITIVE LOGITS
     MAD
    0.75
     SAB
    0.72
     MAC
    0.71
     VID
    0.71
     RIC
    0.71
     NAP
    0.69
     MAM
    0.68
     CAB
    0.68
     SAM
    0.68
     BAT
    0.67
    Activations Density 1.524%

    No Known Activations