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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 3031
    Prev
    Next
    INDEX
    Explanations

    information related to government and political representatives

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

    Following a title or a name

    np_acts-logits-general · gemini-2.0-flash

    spokesperson or representative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.75
     समीक्षाएं
    -0.68
    ArgsConstructor
    -0.67
     riuscito
    -0.65
    SBATCH
    -0.65
     BrowserModule
    -0.64
    UrlResolution
    -0.63
     quelquefois
    -0.62
    resave
    -0.61
    iança
    -0.61
    POSITIVE LOGITS
     spokesperson
    1.11
     spokeswoman
    1.08
     spokesman
    1.07
     Spokes
    0.89
     spokespersons
    0.83
     spokes
    0.78
    Spo
    0.75
     portavoz
    0.74
     reps
    0.62
    Representatives
    0.60
    Activations Density 0.164%

    No Known Activations