© 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. 9-GEMMASCOPE-RES-16K
    11. 15939
    Prev
    Next
    INDEX
    Explanations

    time and date references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chancel
    -0.45
    ORDS
    -0.44
     licked
    -0.43
     Luego
    -0.43
     poivre
    -0.39
     שלי
    -0.38
     inferiore
    -0.38
     inimes
    -0.38
     druž
    -0.38
     sacerdote
    -0.37
    POSITIVE LOGITS
    تقاوى
    1.11
     kasarigan
    0.98
     ModelExpression
    0.94
     Roskov
    0.91
    MENAFN
    0.83
     AssemblyCulture
    0.82
    发表于
    0.82
    rungsseite
    0.81
     tartalomajánló
    0.81
    verwijspagina
    0.80
    Activations Density 0.483%

    No Known Activations