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. 10-GEMMASCOPE-RES-16K
    6. 2975
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to duration and limits of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.56
    migrationBuilder
    -0.55
    /**
    -0.54
     CreateTagHelper
    -0.54
     Herald
    -0.53
     Straf
    -0.51
    UFF
    -0.50
    #+#
    -0.50
    tog
    -0.49
    MENAFN
    -0.49
    POSITIVE LOGITS
     duration
    1.14
     longer
    1.09
     durée
    1.07
     length
    1.04
     longest
    0.95
     durations
    0.92
    longer
    0.89
     Duration
    0.88
    Longer
    0.88
    duration
    0.86
    Activations Density 0.707%

    No Known Activations