© 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. 822
    Prev
    Next
    INDEX
    Explanations

    phrases related to cost, expenses, and financial considerations

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

    "is" followed by an article

    np_acts-logits-general · gemini-2.0-flash

    is inevitable, definitely, key

    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
    پس
    -0.58
    like
    -0.53
     betweenstory
    -0.49
    Like
    -0.48
     vidi
    -0.47
     Desta
    -0.46
    ようだ
    -0.45
    Distrito
    -0.45
    pile
    -0.44
     congenial
    -0.44
    POSITIVE LOGITS
    protoimpl
    0.78
     something
    0.74
    principalColumn
    0.72
    addGap
    0.68
    Билгалдахарш
    0.63
     auxquelles
    0.61
    Something
    0.61
    OrBuilder
    0.61
     inégal
    0.60
    ValueGenerated
    0.60
    Activations Density 0.211%

    No Known Activations