© 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. 7071
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 'a' in various contexts

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

    Tokens following the letter "a"

    np_acts-logits-general · gemini-2.0-flash

    a mathematical term

    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
    queles
    -0.58
    quela
    -0.58
     estime
    -0.57
    quilo
    -0.56
    ly
    -0.52
     úgy
    -0.48
     either
    -0.47
     interesting
    -0.47
    StartsWith
    -0.46
     ever
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.85
     estekak
    0.74
    dirond
    0.73
     ModelExpression
    0.72
     priori
    0.72
     Audiodateien
    0.71
    DockStyle
    0.70
     مشين
    0.70
    脚注の使い方
    0.70
    iprot
    0.69
    Activations Density 0.413%

    No Known Activations