Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12629
    Prev
    Next
    INDEX
    Explanations

    discussion of artificial intelligence and its implications for technology

    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
    AsUp
    -0.73
     betweenstory
    -0.63
     familiare
    -0.61
     provisoire
    -0.57
     AttributeSet
    -0.56
    TextInputLayout
    -0.55
     scoreless
    -0.53
     recev
    -0.53
    Santis
    -0.52
     Paused
    -0.52
    POSITIVE LOGITS
     technologies
    1.05
     technology
    0.99
     technological
    0.84
    technology
    0.75
    .*")]
    0.73
     advancements
    0.73
     developments
    0.72
     Technology
    0.72
     للمعارف
    0.70
    technologies
    0.70
    Activations Density 0.555%

    No Known Activations