© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5695
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "various" and related inflected forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.62
     Absolute
    -0.57
    absolute
    -0.56
     absolute
    -0.53
    Absolute
    -0.52
     ABSOL
    -0.50
     Absol
    -0.49
     Roskov
    -0.49
     absolu
    -0.48
     absol
    -0.45
    POSITIVE LOGITS
     various
    1.19
    Various
    1.16
     Various
    1.13
    various
    1.09
     VARIOUS
    0.91
     berbagai
    0.82
    各种
    0.77
    各種
    0.76
     diverses
    0.69
     různých
    0.68
    Activations Density 0.071%

    No Known Activations