© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    structured data or programming constructs involving arrays or vectors

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

    Code, data and markup delimiters

    np_acts-logits-general · gemini-2.0-flash

    code syntax and structure

    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
     (
    -0.54
    <eos>
    -0.51
     but
    -0.44
    ↵
    -0.44
    ↵↵
    -0.44
    res
    -0.42
    /
    -0.42
    n
    -0.41
     $
    -0.41
    .
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.94
     myſelf
    0.88
    URLException
    0.88
     NSCoder
    0.86
    yntaxException
    0.79
     $_"
    0.79
     Cæsar
    0.78
     betweenstory
    0.75
     iſt
    0.75
     Houſe
    0.74
    Activations Density 0.565%

    No Known Activations