© 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. 13828
    Prev
    Next
    INDEX
    Explanations

    references to undercover operations and their associated contexts

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

    references to specific named places or institutions (proper nouns), often including possessive "'s" and formal room/office terms.

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

    possessive forms indicating ownership or association, particularly with proper nouns and specific locations.

    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
     يتيمه
    -0.63
     ModelExpression
    -0.60
    ViewInit
    -0.59
     فريبيس
    -0.56
    ParallelGroup
    -0.54
    ChildScrollView
    -0.54
    stateProvider
    -0.54
    PointerException
    -0.54
     дописавши
    -0.53
    SequentialGroup
    -0.53
    POSITIVE LOGITS
    gemä
    0.38
     Demp
    0.38
     SME
    0.36
     nat
    0.36
     Jun
    0.36
     alma
    0.35
     Nani
    0.35
     lobby
    0.34
     Haz
    0.34
     centre
    0.34
    Activations Density 0.512%

    No Known Activations