© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15807
    Prev
    Next
    INDEX
    Explanations

    references to finite concepts or terms in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.63
    <b>
    -0.54
     bek
    -0.53
    ObjectMapper
    -0.52
    Amos
    -0.52
    ">//
    -0.52
    Mel
    -0.51
    nocache
    -0.51
     victims
    -0.49
    ,//
    -0.49
    POSITIVE LOGITS
     finite
    2.83
    Finite
    2.58
     Finite
    2.55
    finite
    2.51
     finito
    1.70
    有限
    1.51
     有限
    1.38
     finit
    1.25
     finitely
    1.24
    Infinite
    1.18
    Activations Density 0.118%

    No Known Activations