© 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. 21-GEMMASCOPE-RES-16K
    11. 10669
    Prev
    Next
    INDEX
    Explanations

    notable features of applications and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.63
    AndEndTag
    -0.53
     AssemblyCulture
    -0.52
    labus
    -0.50
    fillType
    -0.48
     дописавши
    -0.47
     محفوظة
    -0.47
     تضيفلها
    -0.47
    HostException
    -0.45
    期刊论文
    -0.44
    POSITIVE LOGITS
     software
    0.82
     platform
    0.73
     interface
    0.63
     functionalities
    0.63
     platforms
    0.61
     functionality
    0.61
    software
    0.60
    platform
    0.60
     user
    0.60
     tool
    0.58
    Activations Density 0.839%

    No Known Activations