© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10517
    Prev
    Next
    INDEX
    Explanations

    terms indicating the need for additional investigation or research actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stodd
    -0.41
     someplace
    -0.40
     Espinoza
    -0.37
    自从
    -0.35
    semibold
    -0.34
     idéia
    -0.34
    toplasmic
    -0.33
    )['
    -0.33
    ((((
    -0.33
    ⓧ
    -0.32
    POSITIVE LOGITS
    further
    1.95
     further
    1.94
    Further
    1.70
     Further
    1.67
     FURTHER
    1.52
    FURTHER
    1.46
    进一步
    1.20
    urther
    1.16
     weiter
    1.05
     verder
    1.02
    Activations Density 0.198%

    No Known Activations