© 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. 9-GEMMASCOPE-RES-16K
    11. 12374
    Prev
    Next
    INDEX
    Explanations

    references to physical actions and conditions involving effort and resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions related to extreme effort or intensity, such as "going hard," "full throttle," or "all-out" physical exertion.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.48
     AssemblyCompany
    -0.48
    béco
    -0.45
    BagConstraints
    -0.43
    ricians
    -0.41
    примеча
    -0.40
    кновен
    -0.38
     itſelf
    -0.38
    COUVER
    -0.37
    󠁳
    -0.37
    POSITIVE LOGITS
    全力
    0.66
    maximal
    0.59
     Fully
    0.56
    effort
    0.53
     effort
    0.52
     Maximal
    0.52
     maximal
    0.52
    Maximum
    0.52
    เต็ม
    0.52
     Maximum
    0.51
    Activations Density 0.284%

    No Known Activations