© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8926
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify and highlight the presence of population statistics, particularly involving halves and thirds

    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
     estekak
    -0.77
    UpInside
    -0.75
    AutoScaleMode
    -0.74
    estacks
    -0.66
     Augusta
    -0.64
    cektir
    -0.63
    مصادر
    -0.60
    ebilir
    -0.59
     CURIAM
    -0.58
    quiao
    -0.58
    POSITIVE LOGITS
     halfway
    0.91
     Hälfte
    0.90
     half
    0.87
     moitié
    0.85
     mitad
    0.82
     metade
    0.77
     helft
    0.76
     halv
    0.75
    Half
    0.70
    一半
    0.68
    Activations Density 0.195%

    No Known Activations