© 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. 10549
    Prev
    Next
    INDEX
    Explanations

    specific formatting or markup characters and sections in the text

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

    Text followed by questions

    np_acts-logits-general · gemini-2.0-flash

    winner, remarkable success, beliefs

    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
     ―――――
    -1.26
     Efq
    -1.23
     $_"
    -1.22
     purpoſe
    -1.22
    ^(@)
    -1.21
    neſs
    -1.20
     myſelf
    -1.20
     pleaſure
    -1.19
    AsUp
    -1.19
     itſelf
    -1.18
    POSITIVE LOGITS
    <eos>
    0.96
     |
    0.81
    ↵↵
    0.81
    !
    0.79
    ↵↵↵
    0.74
    ?
    0.74
    ↵
    0.69
    ́
    0.66
    </h5>
    0.64
    _
    0.64
    Activations Density 0.268%

    No Known Activations