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

    Neuronpedia

    Jacobian LensNEW
    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. 38-GEMMASCOPE-RES-16K
    11. 10960
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to computer processing or data handling

    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
    #+#
    -0.36
    あえて
    -0.36
    Carriera
    -0.35
    ReusableCell
    -0.34
    FieldNumber
    -0.33
     Chwiliwch
    -0.33
    AsUp
    -0.33
    inSlope
    -0.33
     utafitiHapana
    -0.32
     perus
    -0.32
    POSITIVE LOGITS
     determine
    2.89
     determines
    2.83
     determining
    2.81
    determin
    2.67
    determine
    2.64
     determined
    2.56
     determination
    2.56
     DETERMIN
    2.44
     détermin
    2.42
     determin
    2.39
    Activations Density 2.147%

    No Known Activations