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. 3-GEMMASCOPE-RES-16K
    6. 16238
    Prev
    Next
    INDEX
    Explanations

    references to leadership roles or positions related to chairs and chairpersons

    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
    }}},
    -0.66
    emos
    -0.62
    pezif
    -0.62
    Bullets
    -0.61
    ")){
    
    -0.60
    lehem
    -0.60
    {{{
    -0.58
     بك
    -0.58
    tida
    -0.58
     Molina
    -0.57
    POSITIVE LOGITS
     chair
    3.33
     Chair
    3.22
    Chair
    3.05
     CHAIR
    3.04
     chairs
    3.01
    chair
    2.95
     Chairs
    2.83
    Chairs
    2.58
    CHAIR
    2.51
    chairs
    2.51
    Activations Density 0.039%

    No Known Activations