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. 24-GEMMASCOPE-RES-16K
    6. 2226
    Prev
    Next
    INDEX
    Explanations

    references to locations and political contexts, particularly involving specific regions and notable individuals

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

    Follows locations or places

    np_acts-logits-general · gemini-2.0-flash

    State followed by House, Pinellas, Bent, fixed

    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
     presidencial
    -0.63
     présidentielle
    -0.62
    CppCodeGen
    -0.55
    PostBack
    -0.54
     prêmio
    -0.51
     présidenti
    -0.51
     käyt
    -0.50
     nacionais
    -0.50
     gawas
    -0.50
    OnInit
    -0.49
    POSITIVE LOGITS
    ########.
    0.83
     ExecuteAsync
    0.68
     State
    0.61
    EndContext
    0.60
    :✨
    0.59
    allowNull
    0.58
     Commissioner
    0.56
    pexpr
    0.56
     تضيفلها
    0.56
    CloseOperation
    0.56
    Activations Density 0.094%

    No Known Activations