Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11207
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving limits and asymptotic behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.82
    WarningLevel
    -0.73
     useAppContext
    -0.70
    PerformLayout
    -0.67
    RenderAtEndOf
    -0.66
    DropColumn
    -0.65
    المشاركات
    -0.65
    mapStateToProps
    -0.64
    matchCondition
    -0.63
    EndInit
    -0.62
    POSITIVE LOGITS
     infinite
    1.59
     infinity
    1.56
     forever
    1.54
    infty
    1.47
    infinite
    1.36
    ∞
    1.35
    forever
    1.27
    infinity
    1.26
     infinito
    1.25
     Forever
    1.24
    Activations Density 0.476%

    No Known Activations