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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 5824
    Prev
    Next
    INDEX
    Explanations

    terms related to biomedical or health-related treatments and substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cena
    -0.51
    ceny
    -0.48
    loem
    -0.46
     под
    -0.46
     scuro
    -0.45
     Strong
    -0.44
    Strong
    -0.43
     cheeks
    -0.43
    Relief
    -0.42
    STRONG
    -0.42
    POSITIVE LOGITS
     nakalista
    0.99
    مصادر
    0.70
    出版年
    0.70
    tagHelper
    0.69
    findpost
    0.68
    tagHelperRunner
    0.63
    KommentareTeilen
    0.58
     esterni
    0.56
    ,‎
    0.56
     defaultstate
    0.55
    Activations Density 0.132%

    No Known Activations