© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2760
    Prev
    Next
    INDEX
    Explanations

    details about a singer's background and career achievements

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

    associated with singing voices

    np_acts-logits-general · gemini-2.0-flash

    singing and vocal qualities

    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
    RenderAtEndOf
    -0.69
    abestanden
    -0.67
    انيف
    -0.57
    +#+
    -0.56
    >//
    -0.55
     initComponents
    -0.53
    DockStyle
    -0.53
     players
    -0.51
    存于互联网档案馆
    -0.51
     mobilier
    -0.51
    POSITIVE LOGITS
     singing
    1.81
     singers
    1.51
     sung
    1.50
    singing
    1.48
     sings
    1.45
     sang
    1.45
     Singing
    1.44
    Singing
    1.37
     vocal
    1.36
     sing
    1.36
    Activations Density 0.136%

    No Known Activations