© 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. 30-GEMMASCOPE-RES-16K
    11. 15288
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to image processing and manipulation

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

    Code, formulas, or file paths related to plotting

    np_acts-logits-general · gemini-2.0-flash

    plot parameters and bins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.48
    thenia
    -0.38
    iots
    -0.36
    jod
    -0.35
    iffel
    -0.35
    ecy
    -0.34
    DCT
    -0.33
     intStringLen
    -0.33
    ConstraintMaker
    -0.33
     oslo
    -0.33
    POSITIVE LOGITS
     datasets
    0.61
     computationally
    0.59
     trajectories
    0.58
     computational
    0.57
     dataset
    0.57
     perturbed
    0.56
     plots
    0.55
     statistical
    0.54
     parameter
    0.54
     spatially
    0.53
    Activations Density 1.548%

    No Known Activations