© 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. 396
    Prev
    Next
    INDEX
    Explanations

    phrases related to research objectives and specific aims in scientific studies

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

    Indicates the purpose or aim of a study

    np_acts-logits-general · gemini-2.0-flash

    determine aim to investigate

    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
    ########.
    -0.56
    CloseOperation
    -0.54
    сылкі
    -0.52
    ">//
    -0.52
     Мексичка
    -0.52
    曖昧さ回避
    -0.50
     linkovi
    -0.50
    Билгалдахарш
    -0.50
    IsContent
    -0.49
     հղումներ
    -0.49
    POSITIVE LOGITS
     accurate
    0.39
     simplifié
    0.39
     increased
    0.38
     principaux
    0.38
     accurately
    0.38
    CreateIndex
    0.37
     викона
    0.37
     principale
    0.36
     awareness
    0.36
     generalized
    0.36
    Activations Density 0.315%

    No Known Activations