Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43175
    Prev
    Next
    INDEX
    Explanations

    various expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.16
    ؤلاء
    -0.80
    standers
    -0.75
     decembrie
    -0.74
    tioners
    -0.73
    큼
    -0.70
    ligators
    -0.68
    Sinon
    -0.68
     Wheeler
    -0.66
     Пусть
    -0.65
    POSITIVE LOGITS
     love
    1.30
     LOVE
    1.27
    LOVE
    1.22
     Loves
    1.20
     loves
    1.18
     Love
    1.14
    loves
    1.12
    Love
    1.11
    Loves
    1.09
    love
    1.06
    Activations Density 0.017%

    No Known Activations