© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104234
    Prev
    Next
    INDEX
    Explanations

    terms related to areas and region mapping in a programming context

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

    area and sites/extensions used in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.46
     Nación
    -0.40
     spese
    -0.38
     rutina
    -0.37
    OnAdd
    -0.36
    ArgumentParser
    -0.36
    modelBuilder
    -0.36
     typelib
    -0.35
    JAXB
    -0.35
    toBeTruthy
    -0.34
    POSITIVE LOGITS
    Areas
    0.93
     Areas
    0.80
    areas
    0.70
     Мексичка
    0.68
     صوتيه
    0.63
     Area
    0.61
     areas
    0.61
     AREAS
    0.58
    Area
    0.56
    area
    0.53
    Activations Density 0.001%

    No Known Activations