© 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. 59385
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and desire for improvement in relationships and narratives

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

    "I hope" / "I would" / "will"

    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
    extAlignment
    -0.48
     invokingState
    -0.45
    UnsafeEnabled
    -0.45
     diffuse
    -0.43
     zimowa
    -0.43
     GenerationType
    -0.42
    "){
    -0.41
     gracilis
    -0.40
    الصفحه
    -0.39
     turbid
    -0.39
    POSITIVE LOGITS
    الحياه
    0.46
     meille
    0.40
     старости
    0.38
     ब्रेकडाउन
    0.37
     classics
    0.37
    MetaObject
    0.37
    jár
    0.36
    êques
    0.35
     Bor
    0.35
    enschaften
    0.35
    Activations Density 0.034%

    No Known Activations