© 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. 7-GEMMASCOPE-RES-16K
    11. 6478
    Prev
    Next
    INDEX
    Explanations

    references to formal institutions or authoritative sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favors
    -0.70
     isolato
    -0.67
    Rohy
    -0.65
     OSHA
    -0.64
     abstrait
    -0.63
     Lafayette
    -0.62
     îna
    -0.62
     Hiram
    -0.61
     ModelExpression
    -0.60
     exécu
    -0.60
    POSITIVE LOGITS
     realised
    1.32
    Whilst
    1.30
    behaviour
    1.29
     specialises
    1.28
    initialise
    1.28
     tyres
    1.27
     specialise
    1.26
     Whilst
    1.26
    Behaviour
    1.26
     realise
    1.25
    Activations Density 1.696%

    No Known Activations