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. 10-GEMMASCOPE-RES-16K
    6. 13149
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the" or related forms within a text, indicating a focus on the significance of specific subjects or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflexão
    -0.58
     titolata
    -0.57
     officielles
    -0.57
     idéia
    -0.54
     coisa
    -0.53
     autorité
    -0.53
     aquilo
    -0.52
     organizza
    -0.51
     brachy
    -0.51
     réforme
    -0.51
    POSITIVE LOGITS
     widespread
    0.77
     lack
    0.77
    ">:
    0.73
     numerous
    0.72
     varied
    0.72
     considerable
    0.71
    ########.
    0.70
     tremendous
    0.69
     massive
    0.69
     insistence
    0.69
    Activations Density 0.372%

    No Known Activations