© 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. 3-GEMMASCOPE-RES-16K
    11. 10100
    Prev
    Next
    INDEX
    Explanations

    the occurrence of specific phrases and words that may indicate a new or noteworthy context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crapers
    -0.52
     navideñas
    -0.52
     estekak
    -0.50
    RTSN
    -0.47
     vervol
    -0.47
    RetentionPolicy
    -0.47
     naturais
    -0.47
    RemoveField
    -0.46
     defaultstate
    -0.46
    apkamer
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.47
    참고
    0.41
     lenker
    0.40
    twimg
    0.40
     dis
    0.39
    tanleria
    0.39
    Билгалдахарш
    0.36
    angk
    0.35
    プリング
    0.34
    {§
    0.34
    Activations Density 2.442%

    No Known Activations