© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 12943
    Prev
    Next
    INDEX
    Explanations

    quantifiers and comparative adverbs related to statistical likelihoods

    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
    AndEndTag
    -0.87
    esModule
    -0.82
    PerformLayout
    -0.82
    UIControlState
    -0.78
    addContainerGap
    -0.72
    yargs
    -0.67
    MLLoader
    -0.67
     QtCore
    -0.67
     JpaRepository
    -0.66
     يتيمه
    -0.65
    POSITIVE LOGITS
     than
    1.60
     THAN
    0.98
    than
    0.94
    Than
    0.94
     Than
    0.93
     niż
    0.89
    THAN
    0.83
     kuin
    0.71
     hơn
    0.69
     daripada
    0.67
    Activations Density 0.288%

    No Known Activations