© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10222
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "a" and variations of it, indicating a focus on countable nouns or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asimismo
    -0.76
     perciò
    -0.75
     pertanto
    -0.70
     fometimes
    -0.60
     ciasc
    -0.59
     dunque
    -0.59
     thereon
    -0.58
     tuttavia
    -0.57
     itſelf
    -0.55
     henceforth
    -0.54
    POSITIVE LOGITS
     nice
    1.10
     lot
    1.05
     really
    1.01
     little
    1.00
     few
    0.99
     bit
    0.98
     pretty
    0.93
     REALLY
    0.90
     couple
    0.90
     very
    0.87
    Activations Density 0.369%

    No Known Activations