© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15537
    Prev
    Next
    INDEX
    Explanations

    terms related to promotional or preview content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opat
    -0.75
    irchen
    -0.73
    icoot
    -0.68
    obar
    -0.64
    Бар
    -0.64
    yari
    -0.64
    toch
    -0.63
    ртуаль
    -0.63
     خارجية
    -0.62
    cobacterium
    -0.61
    POSITIVE LOGITS
     Preview
    1.24
     preview
    1.23
     previews
    1.22
     trailers
    1.18
     PREVIEW
    1.16
    Previews
    1.14
     Trailers
    1.13
    Preview
    1.10
     Trailer
    1.09
    PREVIEW
    1.07
    Activations Density 0.082%

    No Known Activations