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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15962
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to duration and longevity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    duration or time

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndProject
    -0.53
    EndGlobalSection
    -0.48
     Simult
    -0.47
    IVEREF
    -0.47
     depositphotos
    -0.47
    "}")
    -0.44
    Jeografia
    -0.44
    ]')
    -0.43
     ivelany
    -0.43
     &___
    -0.42
    POSITIVE LOGITS
     longer
    1.33
    longer
    1.04
     longest
    0.95
     forever
    0.94
    Longer
    0.93
     Longer
    0.90
     dłu
    0.82
     FOREVER
    0.80
    longest
    0.79
     indefinitely
    0.78
    Activations Density 0.182%

    No Known Activations