© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    terms related to election and political outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angkap
    -0.38
    option
    -0.37
    GIVEREF
    -0.36
    unif
    -0.35
    hammer
    -0.35
    ცი
    -0.35
     Cochin
    -0.34
    Option
    -0.34
    Rank
    -0.33
     rank
    -0.33
    POSITIVE LOGITS
    IBAction
    0.62
     שוליים
    0.55
     CanadaChoose
    0.52
    pexpr
    0.50
    總統
    0.47
    hyrchwyd
    0.47
     SYLLABLE
    0.46
    PYX
    0.45
    ]")]
    0.45
    tvguidetime
    0.44
    Activations Density 0.313%

    No Known Activations