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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 15940
    Prev
    Next
    INDEX
    Explanations

    references to detailed descriptions or analyses

    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
     CreateTagHelper
    -0.89
     magasiner
    -0.74
     downvotes
    -0.67
    SUPPLY
    -0.66
     Schmer
    -0.65
    ाहरण
    -0.65
     artifice
    -0.65
     Hermitage
    -0.64
     divinity
    -0.63
     Nema
    -0.63
    POSITIVE LOGITS
     detailed
    2.21
     Detailed
    1.96
    detailed
    1.94
    Detailed
    1.89
     accurate
    1.29
     comprehensive
    1.23
     thorough
    1.09
     détaillé
    1.08
     detalla
    1.08
     detalladas
    1.06
    Activations Density 0.105%

    No Known Activations