© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 448
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating repetition or emphasis

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

    "another"

    np_acts-logits-general · gemini-2.0-flash

    another, same, or different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.58
    省市镇
    -0.54
    verifyException
    -0.49
    KommentareTeilen
    -0.48
    MemoryWarning
    -0.48
    initions
    -0.47
     Anexo
    -0.46
    migrationBuilder
    -0.46
    colhead
    -0.46
    ValueGenerated
    -0.45
    POSITIVE LOGITS
    Another
    0.50
     Another
    0.47
    another
    0.47
     another
    0.46
    同様に
    0.38
    圳
    0.37
    altra
    0.35
    complexContent
    0.35
    ditto
    0.34
     McIl
    0.34
    Activations Density 0.381%

    No Known Activations