© 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. 14818
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations involving indexing and notation

    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
     للمعارف
    -0.99
     Wund
    -0.70
     pank
    -0.68
    رح
    -0.67
     setLoading
    -0.66
     kark
    -0.66
     tork
    -0.65
     Theſe
    -0.65
    Ven
    -0.63
     desac
    -0.63
    POSITIVE LOGITS
     i
    1.32
    I
    1.21
     I
    1.18
     iArr
    1.06
     iVar
    0.99
    iI
    0.90
    튿
    0.88
     jLabel
    0.86
    i
    0.86
    itage
    0.85
    Activations Density 0.211%

    No Known Activations