© 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 EvalsExportsinterp-engineNEWAPI 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. 37633
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "ian" in words, indicating a focus on specific fields or classifications

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

    words ending in ian

    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
     corse
    -0.45
    estors
    -0.41
     loto
    -0.40
     climatique
    -0.39
     franz
    -0.38
    antası
    -0.38
    cerned
    -0.38
    gings
    -0.38
    GIVEREF
    -0.37
     Tibet
    -0.36
    POSITIVE LOGITS
    onian
    0.80
    mannian
    0.69
     zijne
    0.64
    udian
    0.63
    lacian
    0.62
    providedIn
    0.58
     '{@
    0.57
    ⓧ
    0.56
    conian
    0.56
    inian
    0.55
    Activations Density 0.097%

    No Known Activations