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. 6-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    concepts related to silence and empty spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↩
    -0.68
    KommentareTeilen
    -0.64
    Portale
    -0.63
     تانيه
    -0.63
    קישורים
    -0.62
     AttributeSet
    -0.61
    endphp
    -0.60
     autorytatywna
    -0.60
    Portail
    -0.60
     vigueur
    -0.58
    POSITIVE LOGITS
     absence
    1.01
     blank
    0.98
     silence
    0.96
     dearth
    0.95
     missing
    0.92
     Absence
    0.92
     lack
    0.87
    缺
    0.86
    absence
    0.86
     emptiness
    0.85
    Activations Density 0.546%

    No Known Activations