© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1588
    Prev
    Next
    INDEX
    Explanations

    concepts related to empowerment and ownership

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

    "creative" or "business" appearing before a variety of words

    np_acts-logits-general · gemini-2.0-flash

    creative outlet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.68
    tagHelperRunner
    -0.67
    titian
    -0.64
    ̈́
    -0.62
    ніципалі
    -0.61
    vistar
    -0.61
     Patriotic
    -0.58
    visiae
    -0.57
    bors
    -0.56
    endish
    -0.56
    POSITIVE LOGITS
    évaluateur
    0.36
    aarrggbb
    0.35
     dueño
    0.32
     pinulongan
    0.32
    ArrowToggle
    0.30
     héroe
    0.28
    XmlElement
    0.28
    afficheront
    0.28
    DataAnnotations
    0.28
     समीक्षाओं
    0.27
    Activations Density 0.409%

    No Known Activations