© 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. 128324
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance of an issue or situation, particularly emphasizing whether it is a "big deal" or not

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

    no big deal or harm

    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
     nonUne
    -0.60
     surla
    -0.59
     MaterialApp
    -0.58
    KommentareTeilen
    -0.56
    Kjelder
    -0.55
    ########.
    -0.55
     ModelExpression
    -0.54
    Autoritní
    -0.52
     createSlice
    -0.52
     Comprometido
    -0.51
    POSITIVE LOGITS
     harmless
    0.63
     innoc
    0.41
     nothing
    0.40
     insignificant
    0.40
    没事
    0.39
     innocently
    0.38
     problemlos
    0.38
     Nothing
    0.37
     Miscellaneous
    0.37
    没什么
    0.37
    Activations Density 0.055%

    No Known Activations