© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 106838
    Prev
    Next
    INDEX
    Explanations

    references to crystalline structures and materials

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

    crystalline structure and materials

    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
     Majefty
    -0.62
     purpoſe
    -0.56
    ähteet
    -0.55
     raiſ
    -0.52
     Eſ
    -0.50
    ltä
    -0.49
    setLabel
    -0.49
     paſſ
    -0.48
     détour
    -0.47
     Sünde
    -0.47
    POSITIVE LOGITS
    stalline
    2.02
     crystalline
    1.82
    crystalline
    1.76
     amorphous
    0.88
     crystall
    0.84
    phous
    0.78
    دانشنامهٔ
    0.69
    prepareStatement
    0.68
    orative
    0.66
     Cry
    0.65
    Activations Density 0.009%

    No Known Activations