© 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. 36092
    Prev
    Next
    INDEX
    Explanations

    phrases that convey positivity and care in various contexts

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

    setting the standard

    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
     CreateTagHelper
    -0.88
    IntoConstraints
    -0.84
    httphttps
    -0.82
    RenderAtEndOf
    -0.82
     betweenstory
    -0.81
     EconPapers
    -0.76
    featureID
    -0.74
    aarrggbb
    -0.72
    GOTREF
    -0.69
    Hauptartikel
    -0.68
    POSITIVE LOGITS
    2
    0.30
     excellence
    0.30
    cast
    0.29
    1
    0.29
     réuss
    0.29
     profession
    0.29
    VarChar
    0.29
    !
    0.28
     |
    0.28
     diper
    0.28
    Activations Density 0.160%

    No Known Activations