© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5164
    Prev
    Next
    INDEX
    Explanations

    references to scanning and imaging processes

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

    "scanning" and related terms

    np_acts-logits-general · gemini-2.0-flash

    scanning documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     đình
    -0.29
    dorf
    -0.28
     kelle
    -0.27
     vérit
    -0.27
     Vì
    -0.26
    rippa
    -0.26
    MF
    -0.26
     מוס
    -0.26
     moyens
    -0.25
     propriétés
    -0.25
    POSITIVE LOGITS
     scan
    2.36
     scanning
    2.25
     scans
    2.13
     Scan
    2.11
    scan
    2.06
     Scanning
    2.05
     scanned
    2.05
    Scan
    2.05
     SCAN
    2.03
    scanning
    2.03
    Activations Density 0.217%

    No Known Activations