© 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. 15-GEMMASCOPE-RES-16K
    11. 4884
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vogel
    -0.58
     Dunne
    -0.57
     car
    -0.51
     ISNI
    -0.49
     CanadaChoose
    -0.49
     pic
    -0.48
     mang
    -0.47
    Embeddable
    -0.47
     g
    -0.47
     bug
    -0.47
    POSITIVE LOGITS
     myſelf
    0.86
     iſt
    0.79
     itſelf
    0.79
    ſelf
    0.77
     HasFactory
    0.77
     ſaid
    0.77
     chofe
    0.76
     Савезне
    0.74
     whoſe
    0.74
     obſ
    0.73
    Activations Density 0.340%

    No Known Activations