© 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. 14836
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to mathematical or scientific expressions and representations

    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
     b
    -0.61
     in
    -0.57
     H
    -0.55
     P
    -0.54
     for
    -0.54
     at
    -0.53
     B
    -0.53
     f
    -0.53
     or
    -0.52
     confirm
    -0.52
    POSITIVE LOGITS
     Савезне
    1.39
     Efq
    1.22
     myſelf
    1.17
     itſelf
    1.11
     themſelves
    1.00
     Jefus
    1.00
     Monfieur
    0.99
    ſelf
    0.98
     Majefty
    0.96
     ſhould
    0.93
    Activations Density 1.855%

    No Known Activations