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. 5-GEMMASCOPE-RES-16K
    6. 2497
    Prev
    Next
    INDEX
    Explanations

    names and terminology related to artistic and educational subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reciclaje
    -0.84
    __(/*!
    -0.81
    WriteBarrier
    -0.77
    träd
    -0.77
     Merr
    -0.74
     étrangère
    -0.74
    [...,
    -0.74
     fédé
    -0.73
     astronomers
    -0.73
     Sted
    -0.72
    POSITIVE LOGITS
    Saul
    0.72
     Saul
    0.69
    auri
    0.65
     Erd
    0.65
    Cas
    0.64
     Tyson
    0.64
     György
    0.64
    Tyson
    0.63
     Тай
    0.61
    zou
    0.60
    Activations Density 2.427%

    No Known Activations