© 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. 20-GEMMASCOPE-RES-131K
    11. 58360
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to plumbing and home maintenance

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

    public key or load balancer

    np_acts-logits-general · gemini-2.5-flash-lite

    Finds concrete objects/components — names of parts, materials, tools, or other technical/item nouns.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    mentions of specific technical objects, parts, product names, or other concrete technical terms.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ilustracja
    -0.59
     miniaturka
    -0.57
    AddTagHelper
    -0.53
    ReusableCell
    -0.53
    jména
    -0.52
    DockStyle
    -0.51
     收納
    -0.51
    Numerade
    -0.50
     ilustracji
    -0.50
    genossen
    -0.50
    POSITIVE LOGITS
    UserScript
    0.41
    Havolalar
    0.40
     surla
    0.35
    adone
    0.35
    ‍
    0.35
    oa̍t
    0.34
    цездатний
    0.33
    InjectMocks
    0.33
    胡
    0.32
    ////////////////
    0.32
    Activations Density 0.072%

    No Known Activations