© 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. 24-GEMMASCOPE-RES-16K
    11. 8661
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to software and digital content

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

    Two-letter combinations ending with "w"

    np_acts-logits-general · gemini-2.0-flash

    words starting with 'a' or 'o' followed by 'w'

    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
    basicConfig
    -0.67
     Leger
    -0.65
    TemporalType
    -0.62
    retin
    -0.59
    tisti
    -0.58
    RegistryLite
    -0.57
    Berger
    -0.57
    richlet
    -0.57
     PTI
    -0.57
    STI
    -0.57
    POSITIVE LOGITS
    aw
    0.77
    ow
    0.74
    ew
    0.71
     Lw
    0.69
     Jow
    0.66
     Caw
    0.64
     Daw
    0.62
    ww
    0.62
     Flow
    0.60
     Tow
    0.59
    Activations Density 0.495%

    No Known Activations