© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15022
    Prev
    Next
    INDEX
    Explanations

    references to spiritual or existential concepts related to identity and belonging

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

    emphatic set phrases and rhetorical constructions, especially fixed expressions highlighted by capitalization, quotes, slashes, or hyphens that assert identity, contrast groups, or frame hypotheticals.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    hypothetical or counterfactual expressions, particularly those involving "almost," "could/would/should," "what if," or quotations contrasting opposing groups.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    utives
    -0.52
    enetrable
    -0.52
    copically
    -0.50
     τῆς
    -0.49
    ukone
    -0.49
    IZABETH
    -0.48
     Chwiliwch
    -0.48
     SLP
    -0.46
     zoude
    -0.46
     snippetHide
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.54
     Economía
    0.40
     plazos
    0.39
     Werkstatt
    0.39
     okuyayım
    0.39
     ujednoznacz
    0.38
     trône
    0.38
     profesión
    0.37
     Arzt
    0.37
    todo
    0.37
    Activations Density 0.432%

    No Known Activations