© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14171
    Prev
    Next
    INDEX
    Explanations

    terms related to expansion or extension in various contexts

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

    "extend" or "extending"

    np_acts-logits-general · gemini-2.0-flash

    extending applicability or reach

    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
    GORITH
    -0.52
    ագրություններ
    -0.50
    HttpStatus
    -0.47
    脚注の使い方
    -0.46
    QMetaType
    -0.46
     onPage
    -0.45
    NameValuePair
    -0.43
    yticks
    -0.41
    columnHeader
    -0.40
    Rhestr
    -0.40
    POSITIVE LOGITS
     extend
    1.17
     Extend
    1.14
    Extend
    1.12
    extend
    1.07
    Extended
    1.03
     extended
    1.02
     Extended
    1.02
    extended
    1.02
     extender
    0.98
     extends
    0.95
    Activations Density 0.158%

    No Known Activations