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. 23-GEMMASCOPE-RES-16K
    6. 5758
    Prev
    Next
    INDEX
    Explanations

    contradictions or contrasting statements

    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
     zwar
    -0.93
     sice
    -0.72
     оригіналу
    -0.68
     übrigens
    -0.68
     even
    -0.64
     além
    -0.62
    だけでなく
    -0.61
    even
    -0.60
    はもちろん
    -0.60
     nejen
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.97
     nevertheless
    1.90
     dennoch
    1.32
    それでも
    1.27
    Nonetheless
    1.22
     trotzdem
    1.20
    Nevertheless
    1.17
     néanmoins
    1.17
     зато
    1.16
     ändå
    1.16
    Activations Density 0.372%

    No Known Activations