© 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. 20-GEMMASCOPE-RES-16K
    11. 862
    Prev
    Next
    INDEX
    Explanations

    specific formatting or markers in the text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by words starting with lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    CALIBRATION, vector, parents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.09
     R
    -0.86
     O
    -0.84
     M
    -0.82
     I
    -0.82
     T
    -0.81
     E
    -0.81
     L
    -0.80
     B
    -0.80
     H
    -0.79
    POSITIVE LOGITS
     itſelf
    1.70
     myſelf
    1.64
     pleaſure
    1.49
     Monfieur
    1.42
     ་་
    1.41
     ſeveral
    1.38
     doubtnut
    1.37
     greateſt
    1.37
     themſelves
    1.34
     ſmall
    1.34
    Activations Density 0.215%

    No Known Activations