© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 15851
    Prev
    Next
    INDEX
    Explanations

    terms related to campaign finance and political conduct regulations

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

    Constitutional law, especially challenges and scrutiny

    np_acts-logits-general · gemini-2.0-flash

    constitutional scrutiny and challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.71
    ellschaft
    -0.60
     fundido
    -0.58
    MetaObject
    -0.54
    DotNetBar
    -0.54
     OMIT
    -0.53
     оригіналу
    -0.52
     disambiguazione
    -0.51
    Aholisi
    -0.51
     "..\..\
    -0.50
    POSITIVE LOGITS
     uncons
    0.71
     constitutional
    0.70
     estekak
    0.65
     constitution
    0.61
     invalid
    0.61
     Fourteenth
    0.59
    invalid
    0.57
     Verfassung
    0.54
     Congress
    0.52
    jsonwebtoken
    0.51
    Activations Density 2.222%

    No Known Activations