© 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. 11-GEMMASCOPE-RES-16K
    11. 12875
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific algorithm or data structure within code, particularly those associated with 'mantis.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >{@
    -1.00
    IPAC
    -0.97
    ymce
    -0.95
    GEBURTSDATUM
    -0.95
    erializer
    -0.81
    PerformLayout
    -0.81
    principalTable
    -0.71
    loroethane
    -0.71
    DockStyle
    -0.70
    ufact
    -0.70
    POSITIVE LOGITS
     becauſe
    0.95
     whoſe
    0.90
     modelAndView
    0.89
     Efq
    0.87
     dataSnapshot
    0.85
     himſelf
    0.82
     Majefty
    0.82
     rootReducer
    0.82
     itſelf
    0.81
    Autoritní
    0.81
    Activations Density 1.786%

    No Known Activations