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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6270
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riwal
    -0.90
     '\\;'
    -0.86
    aarrggbb
    -0.80
    Diweddarwch
    -0.77
     nawr
    -0.73
    RetentionPolicy
    -0.70
     وتسجيلات
    -0.69
     JpaRepository
    -0.69
    ніципа
    -0.68
    hashtags
    -0.67
    POSITIVE LOGITS
     past
    1.93
     Past
    1.92
    past
    1.86
    Past
    1.77
     PAST
    1.67
    PAST
    1.48
     future
    1.17
    Future
    1.16
     Future
    1.16
     FUTURE
    1.10
    Activations Density 0.141%

    No Known Activations