© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8990
    Prev
    Next
    INDEX
    Explanations

    specific sequences of numerical data or measurements

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

    The number 7

    np_acts-logits-general · gemini-2.0-flash

    numbers ending in 7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ConstraintMaker
    -0.80
    帖最后由
    -0.80
    клопе
    -0.77
     EconPapers
    -0.71
    PasswordEncoder
    -0.71
    Ārējās
    -0.70
     Sixteenth
    -0.67
    AnchorStyles
    -0.65
     sixteenth
    -0.64
     imageNamed
    -0.63
    POSITIVE LOGITS
    7
    1.76
     Seven
    1.48
     seven
    1.44
     SEVEN
    1.28
    Seven
    1.27
     tujuh
    1.21
    seven
    1.20
    七
    1.20
    ７
    1.18
     seventh
    1.18
    Activations Density 1.139%

    No Known Activations