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. 25-GEMMASCOPE-RES-16K
    6. 10358
    Prev
    Next
    INDEX
    Explanations

    phrases or segments that mention the concepts of assistance, need, and emotional states in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.80
    //
    -0.66
     Subsequent
    -0.64
     Thereafter
    -0.58
     précédentes
    -0.58
    gameserver
    -0.56
     veille
    -0.56
     indisponible
    -0.56
     Previous
    -0.56
    InjectAttribute
    -0.55
    POSITIVE LOGITS
     right
    2.83
     currently
    2.45
    right
    2.15
     presently
    2.10
    currently
    2.09
     atm
    2.02
    Right
    2.01
     rn
    2.01
     Right
    1.97
     Currently
    1.94
    Activations Density 0.645%

    No Known Activations