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. 18-GEMMASCOPE-RES-16K
    6. 1548
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their achievements

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

    Tokens after names like Sharpton, Jackson, or Farrakhan

    np_acts-logits-general · gemini-2.0-flash

    African American figures and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    landaise
    -0.55
     مرئيه
    -0.54
    MLLoader
    -0.51
    AUSTR
    -0.50
     tchèque
    -0.50
     pares
    -0.49
     AUSTR
    -0.49
    httphttps
    -0.45
    critto
    -0.45
     InputDecoration
    -0.45
    POSITIVE LOGITS
    🏾
    1.59
     Afro
    1.28
     African
    1.27
    🏿
    1.24
     afro
    1.20
    African
    1.16
     NAACP
    1.16
    Afro
    1.12
     Harlem
    1.04
     Negroes
    1.03
    Activations Density 0.742%

    No Known Activations