© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare research and community engagement

    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
     consiste
    -0.32
     bedo
    -0.32
     convinces
    -0.30
     convince
    -0.29
     رس
    -0.29
     предпочита
    -0.29
     contribué
    -0.28
     состоя
    -0.28
    AnchorStyles
    -0.28
     consigue
    -0.27
    POSITIVE LOGITS
     poses
    2.22
     pose
    2.16
     posed
    1.89
     posing
    1.87
     Pose
    1.69
    poses
    1.53
     presents
    1.52
    Pose
    1.48
    pose
    1.48
    presents
    1.34
    Activations Density 1.132%

    No Known Activations