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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10143
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding a contrastive conjunction

    np_acts-logits-general · gemini-2.0-flash

    not X but Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.61
    исленность
    -0.59
    λών
    -0.54
     pinulongan
    -0.53
     насељу
    -0.53
    pedes
    -0.53
    urman
    -0.53
    falen
    -0.52
    κης
    -0.52
    epik
    -0.51
    POSITIVE LOGITS
     بلکه
    1.81
    而是
    1.54
     sondern
    1.52
     melainkan
    1.24
     אלא
    1.13
     vaan
    1.10
     hanem
    0.99
     Rather
    0.81
     Instead
    0.76
     necessarily
    0.74
    Activations Density 0.308%

    No Known Activations