© 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. 35-GEMMASCOPE-RES-16K
    11. 7271
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    ArrowToggle
    -0.51
     unknownFields
    -0.48
    RenderAtEndOf
    -0.47
     كومونز
    -0.46
     հղումներ
    -0.43
    NameInMap
    -0.43
    SharedCtor
    -0.43
     дописавши
    -0.42
    POSITIVE LOGITS
     s
    1.20
     ſhe
    0.87
     그녀
    0.85
     she
    0.84
    她們
    0.83
    herself
    0.82
     herself
    0.79
    她们
    0.75
     her
    0.75
    她
    0.71
    Activations Density 0.493%

    No Known Activations