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. 3-GEMMASCOPE-RES-16K
    6. 12913
    Prev
    Next
    INDEX
    Explanations

    references to the Senate and its processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.63
    Хьажоргаш
    -0.62
    TagHelper
    -0.60
    Slf
    -0.58
     brin
    -0.57
    FLICT
    -0.56
     resourceCulture
    -0.56
    startswith
    -0.56
    Visitors
    -0.56
    ukup
    -0.55
    POSITIVE LOGITS
     Senate
    2.65
     senate
    2.42
    Senate
    2.25
     senators
    2.23
    Sen
    2.22
     senator
    2.21
     Sen
    2.19
     SENATE
    2.14
     sen
    2.12
     Senators
    2.10
    Activations Density 0.098%

    No Known Activations