© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    variations of the word "ange" across different contexts or forms

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

    ange and anger

    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
    ◀
    -0.38
    ')))
    -0.36
     disfrut
    -0.36
    windowFixed
    -0.33
    ://
    -0.31
     disfr
    -0.30
    ')")
    -0.30
    ✼
    -0.29
    '],'
    -0.29
     gehouden
    -0.29
    POSITIVE LOGITS
    ange
    2.78
    ANGE
    2.16
    anges
    1.91
    anger
    1.72
    Ange
    1.69
     ange
    1.63
     Ange
    1.58
    angi
    1.50
    anged
    1.47
    anging
    1.47
    Activations Density 0.008%

    No Known Activations