© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3046
    Prev
    Next
    INDEX
    Explanations

    the conjunctions "and" and "or" in the text

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

    Tokens immediately after "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions `and` or `or`

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     noastre
    -0.44
     dieselbe
    -0.41
     plateado
    -0.40
     useAppContext
    -0.40
     nostru
    -0.38
     selben
    -0.37
     dasselbe
    -0.36
     derselben
    -0.36
    UrlResolution
    -0.36
     femininas
    -0.36
    POSITIVE LOGITS
    Tembelea
    0.64
    InjectAttribute
    0.64
     organisers
    0.56
    ByVersion
    0.56
    المشاركات
    0.55
     colourful
    0.54
     désolés
    0.53
     propOrder
    0.53
    цезда
    0.53
    colours
    0.53
    Activations Density 0.180%

    No Known Activations