© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15950
    Prev
    Next
    INDEX
    Explanations

    references to names and personal identification in relation to ballots and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     sahiptir
    -0.61
     göre
    -0.53
    empêcher
    -0.48
    sounds
    -0.48
    ugier
    -0.47
    意思是
    -0.47
    enthe
    -0.46
    found
    -0.45
     hittar
    -0.45
     zvuky
    -0.44
    POSITIVE LOGITS
     unfold
    1.08
     emerge
    1.04
     evolve
    0.97
     disappear
    0.89
     happen
    0.89
     come
    0.89
     coming
    0.87
     firsthand
    0.87
     arrive
    0.84
     للمعارف
    0.81
    Activations Density 0.280%

    No Known Activations