© 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. 12-GEMMASCOPE-RES-16K
    11. 2057
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty about beliefs or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.56
    Rujuakan
    -0.56
    RenderAtEndOf
    -0.55
     préfé
    -0.52
    @[+][
    -0.52
    HasAnnotation
    -0.52
     Wikimedijinoj
    -0.51
     المعيارى
    -0.49
    aarrggbb
    -0.48
     vVar
    -0.48
    POSITIVE LOGITS
     (!_
    0.53
     Không
    0.52
     eikä
    0.51
     not
    0.51
     neither
    0.50
     necessarily
    0.50
     Neither
    0.49
     नहीं
    0.47
     Tidak
    0.47
     tidak
    0.47
    Activations Density 1.704%

    No Known Activations