Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2414
    Prev
    Next
    INDEX
    Explanations

    terms related to voter fraud and electoral integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LoggerFactory
    -0.56
    OGND
    -0.51
     Topf
    -0.49
     reuni
    -0.47
    homonymie
    -0.46
     abbraccio
    -0.44
    şiv
    -0.44
     aikaa
    -0.43
     препратки
    -0.43
    ները
    -0.42
    POSITIVE LOGITS
     Electoral
    1.03
     electoral
    1.02
     voter
    0.99
     Voter
    0.93
     ballot
    0.91
    lectoral
    0.90
     Election
    0.89
     ballots
    0.86
     election
    0.80
     Elections
    0.80
    Activations Density 0.227%

    No Known Activations