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. 6429
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, or legislative matters

    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
    memberOf
    -0.59
     oreilles
    -0.57
     peggio
    -0.54
     gambe
    -0.52
     lèvres
    -0.51
     nuages
    -0.51
     résine
    -0.51
     mères
    -0.50
     acciaio
    -0.50
     prisonniers
    -0.49
    POSITIVE LOGITS
     affair
    0.82
     activity
    0.81
     impressions
    0.79
     regime
    0.78
     situation
    0.78
     installations
    0.77
     transactions
    0.77
     atmosphere
    0.77
     mixture
    0.77
     scenario
    0.76
    Activations Density 2.183%

    No Known Activations