© 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. 40-GEMMASCOPE-RES-16K
    11. 2907
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "up" or upward movement in various contexts

    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
     updated
    -0.53
     update
    -0.47
     updates
    -0.47
    ering
    -0.45
    上门
    -0.45
     UPDATED
    -0.45
     updating
    -0.44
    s
    -0.43
     Updated
    -0.43
     upright
    -0.42
    POSITIVE LOGITS
    GRADE
    0.54
    turned
    0.52
    脚注の使い方
    0.51
    tempo
    0.50
    gradable
    0.49
    datable
    0.48
     automatiques
    0.46
    trend
    0.46
    cycling
    0.46
    town
    0.45
    Activations Density 0.234%

    No Known Activations