© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6942
    Prev
    Next
    INDEX
    Explanations

    references to allegations of misconduct and torture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.63
    onViewCreated
    -0.49
    RegistryLite
    -0.48
    queryInterface
    -0.46
    Архівовано
    -0.45
    ToBounds
    -0.45
     lateinit
    -0.44
    
    -0.43
     Vict
    -0.43
    PYX
    -0.43
    POSITIVE LOGITS
     complaining
    0.59
     complains
    0.57
     complained
    0.57
     complaint
    0.56
     confes
    0.56
     forteller
    0.54
     describe
    0.54
     powiedzieć
    0.53
     confesses
    0.53
     complain
    0.52
    Activations Density 0.514%

    No Known Activations