© 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. 9-GEMMASCOPE-RES-16K
    11. 6895
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements of thickness and physical properties of materials

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

    measurements of thickness in technical or descriptive contexts.

    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
    astéroïdes
    -0.89
    ⟬
    -0.83
    iſchen
    -0.78
    ChildScrollView
    -0.77
    ConstraintMaker
    -0.74
    iſche
    -0.71
    HostException
    -0.70
     Geiſt
    -0.69
    niſſe
    -0.69
    contentLoaded
    -0.69
    POSITIVE LOGITS
     thick
    1.67
     thin
    1.52
     Thick
    1.46
    Thick
    1.45
     thicker
    1.44
     thickness
    1.43
    thick
    1.39
    Thickness
    1.36
     Thin
    1.32
    Thin
    1.30
    Activations Density 0.305%

    No Known Activations