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. 23-GEMMASCOPE-RES-16K
    6. 5873
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between values or entities

    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
    autogui
    -0.54
     gill
    -0.48
    ელი
    -0.47
    otti
    -0.47
    usercontent
    -0.46
    executor
    -0.44
    obot
    -0.44
     executor
    -0.44
     endwhile
    -0.43
     Butler
    -0.43
    POSITIVE LOGITS
    9
    1.89
     Nine
    1.66
     nine
    1.62
     ninth
    1.57
     Ninth
    1.56
     NINE
    1.45
     ninety
    1.42
    9
    1.41
    Nine
    1.40
    九
    1.37
    Activations Density 0.844%

    No Known Activations