© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 101444
    Prev
    Next
    INDEX
    Explanations

    keywords related to fields of study and academia, particularly in engineering, architecture, and biomedical contexts

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

    specific domains and sub-categories

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     dévelo
    -0.38
     desecha
    -0.35
     Comprometido
    -0.35
    upné
    -0.33
    ientras
    -0.33
     Cancelar
    -0.33
     tuyo
    -0.32
    erdings
    -0.32
     portait
    -0.31
     distinto
    -0.31
    POSITIVE LOGITS
    romyalgia
    0.71
    IntoConstraints
    0.69
    VersionUID
    0.60
    ChildScrollView
    0.59
    URLException
    0.59
     AssemblyCompany
    0.58
    vernote
    0.58
    躇
    0.57
    sego
    0.57
    fortawesome
    0.57
    Activations Density 5.133%

    No Known Activations