© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106929
    Prev
    Next
    INDEX
    Explanations

    references to candidates in various contexts, particularly related to elections and qualifications

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

    candidate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.53
     Wier
    -0.50
     rust
    -0.43
    ../../
    -0.42
    ../../../
    -0.41
     shuts
    -0.41
    ="../
    -0.40
    troppo
    -0.40
     Urqu
    -0.40
     reír
    -0.39
    POSITIVE LOGITS
     Candidate
    1.32
    Candidate
    1.27
     candidate
    1.20
     Candidates
    1.17
    candidate
    1.10
    Candidates
    1.09
     CANDIDATE
    1.02
     candidature
    1.01
     candidates
    1.01
    andidate
    0.94
    Activations Density 0.010%

    No Known Activations