© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5652
    Prev
    Next
    INDEX
    Explanations

    mentions of groups, teams, or organizations involved in decision-making or significant actions

    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
    enumi
    -0.69
    出版年
    -0.61
    solo
    -0.59
     solo
    -0.55
    Solo
    -0.51
     SOLO
    -0.51
     Solo
    -0.51
    kolwiek
    -0.50
    WebVitals
    -0.49
    inals
    -0.49
    POSITIVE LOGITS
     consisting
    1.50
     composed
    1.44
     comprised
    1.40
     comprising
    1.30
     consisted
    1.27
     terdiri
    1.22
     consists
    1.21
     composta
    1.14
     composto
    1.13
    composed
    1.13
    Activations Density 0.500%

    No Known Activations