© 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. 2-GEMMASCOPE-RES-16K
    11. 1331
    Prev
    Next
    INDEX
    Explanations

    references to specific methods or approaches in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cy
    -0.68
    きましたが
    -0.64
     consommation
    -0.64
     Âge
    -0.63
    لها
    -0.63
     Otis
    -0.62
    Opéra
    -0.60
    cy
    -0.60
    dders
    -0.60
    Slf
    -0.59
    POSITIVE LOGITS
     Techniques
    2.62
     technique
    2.55
     techniques
    2.53
     Technique
    2.53
     TECHNIQUE
    2.44
    Techniques
    2.43
     TECHNIQUES
    2.41
    Technique
    2.28
    techniques
    2.27
    technique
    2.27
    Activations Density 0.063%

    No Known Activations