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. 3-GEMMASCOPE-RES-16K
    6. 8645
    Prev
    Next
    INDEX
    Explanations

    co-authorship relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.86
     Monfieur
    -0.86
     useParams
    -0.86
     fubject
    -0.83
     Chriftian
    -0.78
     myſelf
    -0.77
     itſelf
    -0.77
     Jefus
    -0.75
     ſeveral
    -0.74
     Chriſt
    -0.73
    POSITIVE LOGITS
     co
    3.69
     Co
    2.71
    Co
    2.38
    co
    1.94
     CO
    1.42
     covariates
    1.32
     coc
    1.25
     cof
    1.24
     Cob
    1.21
    CO
    1.19
    Activations Density 0.066%

    No Known Activations