© 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. 8-GEMMASCOPE-RES-16K
    11. 7941
    Prev
    Next
    INDEX
    Explanations

    general indicators of property features and characteristics, such as the number of bedrooms and descriptions of spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.67
    expandindo
    -0.60
    AndEndTag
    -0.56
     odkazy
    -0.55
     Matka
    -0.52
    setVerticalGroup
    -0.50
     NgModule
    -0.49
     godfather
    -0.49
    tvguidetime
    -0.49
     unders
    -0.48
    POSITIVE LOGITS
    DotNetBar
    0.71
     pulumi
    0.68
     JADX
    0.66
    fjspx
    0.58
     الرخصة
    0.55
     cahier
    0.53
     BorderRadius
    0.53
     scolaires
    0.51
    thenReturn
    0.51
    rague
    0.50
    Activations Density 0.055%

    No Known Activations