© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6180
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or doubt

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

    "I don't" or "I don’t"

    np_acts-logits-general · gemini-2.0-flash

    expressing lack of knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.57
     linkovi
    -0.54
    #+#
    -0.52
    <?
    -0.50
     Wikimedijinoj
    -0.49
     архивлан
    -0.47
    posedge
    -0.46
     lizenzfreie
    -0.43
    newBuilder
    -0.42
     
    -0.41
    POSITIVE LOGITS
     know
    0.59
     believe
    0.56
     remember
    0.54
     feel
    0.50
     think
    0.48
     sure
    0.47
     see
    0.45
     disagree
    0.45
    RotationOrder
    0.44
     understand
    0.44
    Activations Density 0.171%

    No Known Activations