© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7488
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and entities, particularly related to the civil rights movement and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enamorado
    -0.46
     llorar
    -0.44
     criatura
    -0.44
     burbujas
    -0.40
     Denken
    -0.40
     Publikum
    -0.40
     disfraces
    -0.40
     plegable
    -0.39
     cuchara
    -0.39
     preparación
    -0.39
    POSITIVE LOGITS
     Beatles
    0.74
     Koran
    0.70
     Great
    0.70
     queſta
    0.70
     Quran
    0.66
     Milky
    0.65
     Louvre
    0.64
     Pelop
    0.63
     CIA
    0.63
     Suez
    0.63
    Activations Density 1.076%

    No Known Activations