© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 926
    Prev
    Next
    INDEX
    Explanations

    references related to missing persons or children

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

    Missing or dead individuals

    np_acts-logits-general · gemini-2.0-flash

    crime and repository

    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
    AddTagHelper
    -0.58
    UnusedPrivate
    -0.50
     بيها
    -0.49
     disambiguazione
    -0.47
     صوتيه
    -0.45
     للاسماء
    -0.42
    ftagPool
    -0.42
    تقاوى
    -0.42
     clearfix
    -0.42
    fromnode
    -0.41
    POSITIVE LOGITS
     JpaRepository
    0.68
     Partagez
    0.43
    findBy
    0.43
    userRepository
    0.42
     indisponible
    0.40
    ToListAsync
    0.40
     homomorphism
    0.39
     userRepository
    0.39
    vanni
    0.39
    NamedQuery
    0.39
    Activations Density 0.228%

    No Known Activations