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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12202
    Prev
    Next
    INDEX
    Explanations

    references to age and the concept of being older

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.78
    <em>
    -0.73
    en
    -0.72
    لع
    -0.68
    <strong>
    -0.66
     la
    -0.66
     “
    -0.65
     al
    -0.64
    pa
    -0.64
    an
    -0.63
    POSITIVE LOGITS
    theless
    1.31
     itſelf
    1.18
    ^(@)
    1.14
     doubtnut
    1.10
     matures
    1.07
     myſelf
    1.07
     Мексичка
    1.05
     themſelves
    1.03
     ―――――
    1.02
    Vidite
    1.02
    Activations Density 0.070%

    No Known Activations