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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15304
    Prev
    Next
    INDEX
    Explanations

    references to specific communities or groups and their beliefs or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœux
    -1.34
     épaules
    -1.30
     pouvoirs
    -1.30
     bienfaits
    -1.25
     bénéfices
    -1.23
     négociations
    -1.16
     attentes
    -1.14
     lèvres
    -1.13
     oreilles
    -1.09
     débats
    -1.09
    POSITIVE LOGITS
     environments
    1.04
     versions
    1.03
     setups
    1.02
     situations
    1.00
     systems
    1.00
     schemes
    0.99
     models
    0.97
     programs
    0.96
     projects
    0.96
     contexts
    0.96
    Activations Density 4.722%

    No Known Activations