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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2183
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a change in state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chegando
    -0.64
     Langue
    -0.61
     căr
    -0.61
    webElementXpaths
    -0.60
    näm
    -0.58
     ftill
    -0.58
     fortfarande
    -0.56
     thither
    -0.56
     sedang
    -0.56
     voraus
    -0.55
    POSITIVE LOGITS
     increasingly
    0.90
     consultato
    0.76
     involved
    0.76
    kannya
    0.74
     become
    0.74
     quite
    0.72
     known
    0.72
     aware
    0.71
     became
    0.70
     acquainted
    0.68
    Activations Density 0.089%

    No Known Activations