© 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. 23-GEMMASCOPE-RES-16K
    6. 6542
    Prev
    Next
    INDEX
    Explanations

    terms and concepts from advanced mathematics, particularly those related to measures, integrals, and functional analysis

    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
    penser
    -0.47
    PerPage
    -0.45
     manifested
    -0.44
    nthesis
    -0.44
     undisclosed
    -0.44
     miss
    -0.43
     distillation
    -0.43
    θει
    -0.43
    lectual
    -0.43
     refills
    -0.42
    POSITIVE LOGITS
     $_{\
    0.68
     TextInputType
    0.62
     StringTokenizer
    0.61
     $_{
    0.61
    MLLoader
    0.60
     Tél
    0.60
     GoogleFonts
    0.59
     ddelweddau
    0.59
    balleur
    0.59
    MessageTagHelper
    0.58
    Activations Density 1.138%

    No Known Activations