© 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. 20-GEMMASCOPE-RES-131K
    11. 38212
    Prev
    Next
    INDEX
    Explanations

    various forms and contexts of the word "type" and its related concepts

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

    type followed by a noun or descriptor

    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
    AnchorStyles
    -0.45
     Reserves
    -0.41
    OGND
    -0.40
    󠁢
    -0.40
    Superficie
    -0.40
     Achilles
    -0.39
    deno
    -0.38
    ISupport
    -0.38
    таратура
    -0.38
    Deque
    -0.37
    POSITIVE LOGITS
     stuff
    0.74
     thingy
    0.71
     thing
    0.69
     gitu
    0.67
    tvguidetime
    0.61
    bootstrapcdn
    0.61
    な感じ
    0.60
     uska
    0.59
     things
    0.57
     whatnot
    0.57
    Activations Density 0.025%

    No Known Activations