© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to specific "terms" in a given 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
    зулта
    -0.46
    printf
    -0.39
    postsleuth
    -0.36
     hipótesis
    -0.34
    InputBorder
    -0.32
    ówn
    -0.30
    istoitu
    -0.30
     nervosa
    -0.29
     sprintf
    -0.29
    domada
    -0.29
    POSITIVE LOGITS
     terms
    0.82
     Terms
    0.75
    terms
    0.72
    Terms
    0.72
    #
    0.65
     المعيارى
    0.64
    TERMS
    0.63
    <?
    0.63
     TERMS
    0.62
     EconPapers
    0.61
    Activations Density 0.057%

    No Known Activations