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. 20-GEMMASCOPE-RES-16K
    6. 2310
    Prev
    Next
    INDEX
    Explanations

    terms related to health, medical care, and community development initiatives

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

    preceding types of regulations or funds

    np_acts-logits-general · gemini-2.0-flash

    legal, health, or financial matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realising
    -0.70
     realised
    -0.69
     realises
    -0.61
     realise
    -0.60
     Favourite
    -0.58
    initialise
    -0.56
     honourable
    -0.56
     centralised
    -0.53
     Organisations
    -0.50
     complètes
    -0.50
    POSITIVE LOGITS
     nakalista
    0.71
     $\$$
    0.70
    GEBURTSDATUM
    0.69
     Mardi
    0.68
    SBATCH
    0.66
     Reſ
    0.65
    .”)
    0.63
     $\&$
    0.63
     $[-
    0.61
    ucoup
    0.61
    Activations Density 0.758%

    No Known Activations