© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11393
    Prev
    Next
    INDEX
    Explanations

    references to visions and visionary concepts within organizational or leadership contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mahd
    -0.69
    brackets
    -0.58
     Aristote
    -0.56
     bounce
    -0.56
     CMC
    -0.54
     empate
    -0.54
     partido
    -0.53
    CMC
    -0.53
     cementerio
    -0.53
    abank
    -0.53
    POSITIVE LOGITS
     vision
    2.73
     Vision
    2.65
     VISION
    2.56
    Vision
    2.46
    vision
    2.26
     visions
    2.12
     Visions
    2.03
    VISION
    2.00
     visión
    1.71
     visione
    1.54
    Activations Density 0.039%

    No Known Activations