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. 22-GEMMASCOPE-RES-16K
    6. 13997
    Prev
    Next
    INDEX
    Explanations

    references to sample sizes in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.73
    ArgsConstructor
    -0.68
    ViewInit
    -0.65
    ParallelGroup
    -0.64
    Aiheesta
    -0.60
     defaultstate
    -0.57
     NavController
    -0.57
    URLException
    -0.57
    Архівовано
    -0.55
    <?,
    -0.53
    POSITIVE LOGITS
     Samples
    1.38
     samples
    1.37
    samples
    1.28
    Samples
    1.24
    SAMPLE
    1.05
     SAMPLES
    1.03
     SAMPLE
    1.03
     Sample
    1.03
    SAMPLES
    0.99
    Sample
    0.95
    Activations Density 0.094%

    No Known Activations