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. 3-GEMMASCOPE-RES-16K
    6. 8866
    Prev
    Next
    INDEX
    Explanations

    references to "future" and aspects related to it

    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
     JpaRepository
    -0.75
    #+#
    -0.72
    arraycopy
    -0.70
    chargez
    -0.70
     GeoNames
    -0.67
     IntelliJ
    -0.66
     dépos
    -0.65
    setCellStyle
    -0.63
    nesty
    -0.60
    NamedQueries
    -0.60
    POSITIVE LOGITS
     future
    3.60
    future
    3.34
    Future
    3.15
     Future
    3.15
     FUTURE
    3.02
    FUTURE
    3.00
     futura
    2.60
     futuro
    2.54
     futur
    2.39
     futures
    2.35
    Activations Density 0.064%

    No Known Activations