© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    dates and chronological markers in historical contexts

    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
    WithMany
    -0.71
    IsContent
    -0.71
    AndEndTag
    -0.69
    Rhestr
    -0.67
    ValueStyle
    -0.65
     queſta
    -0.65
    various
    -0.64
    VYMaps
    -0.63
    SourceChecksum
    -0.63
    majánló
    -0.61
    POSITIVE LOGITS
    penup
    0.38
    NgModule
    0.24
     ComVisible
    0.23
    aarrggbb
    0.23
    tagHelperRunner
    0.20
     InputDecoration
    0.20
    toMatch
    0.20
     fram
    0.20
     imperial
    0.20
     suddenly
    0.19
    Activations Density 0.401%

    No Known Activations