© 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. 9-GEMMASCOPE-RES-131K
    11. 43546
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "README" and associated references within the text

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

    README file references

    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
     utafitiHapana
    -0.65
    djangoproject
    -0.65
    addCriterion
    -0.58
     colorWith
    -0.58
    ImageContext
    -0.56
    Portail
    -0.55
    stylers
    -0.55
    EndContext
    -0.50
    ніципа
    -0.49
    تفصیلات
    -0.49
    POSITIVE LOGITS
    README
    2.53
     README
    2.34
     readme
    1.97
    readme
    1.91
     FAQ
    0.63
     markdown
    0.60
    Makefile
    0.58
     changelog
    0.57
     Makefile
    0.57
     wiki
    0.56
    Activations Density 0.011%

    No Known Activations