© 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. 1-GEMMASCOPE-RES-16K
    11. 8994
    Prev
    Next
    INDEX
    Explanations

    whitespace or blank characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -2.52
     ―――――
    -2.38
     itſelf
    -2.36
    ſelf
    -2.26
     pleaſure
    -2.20
     Anſ
    -2.19
     faſt
    -2.13
     Reſ
    -2.13
     purpoſe
    -2.11
     iſt
    -2.09
    POSITIVE LOGITS
     
    2.75
     "
    1.49
     (
    1.44
      
    1.44
    ↵
    1.44
     “
    1.39
     A
    1.32
     T
    1.26
     '
    1.26
     I
    1.23
    Activations Density 1.761%

    No Known Activations