© 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. 15139
    Prev
    Next
    INDEX
    Explanations

    technical or mechanical components and their interactions in descriptions

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

    Positioning or attachment

    np_acts-logits-general · gemini-2.0-flash

    placed or connected

    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
     líqu
    -0.42
     agujas
    -0.40
     mauva
    -0.39
     abbraccio
    -0.38
     huellas
    -0.38
     actualizaciones
    -0.38
     samman
    -0.37
    gangenen
    -0.37
     LIRE
    -0.36
    brochen
    -0.36
    POSITIVE LOGITS
     placed
    1.23
     placement
    1.10
     placing
    1.02
     Placed
    0.97
    placed
    0.96
     Placement
    0.94
     placements
    0.88
     Placing
    0.87
     inserted
    0.86
     positioned
    0.85
    Activations Density 0.665%

    No Known Activations