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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4623
    Prev
    Next
    INDEX
    Explanations

    instances of the word "definition" and related forms, indicating a focus on terms that describe or clarify concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.68
    ="@+
    -0.56
    lismo
    -0.51
     CascadeType
    -0.51
    didSet
    -0.49
     dishes
    -0.46
    ("}\
    -0.45
    Kelebihan
    -0.45
    Kaieteur
    -0.44
    Datuak
    -0.44
    POSITIVE LOGITS
     definition
    0.88
     defined
    0.83
     Definition
    0.70
    定義
    0.67
     definitions
    0.66
     Defined
    0.65
    定义
    0.65
    definition
    0.64
     DEFINITION
    0.62
    defined
    0.62
    Activations Density 0.321%

    No Known Activations