© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8872
    Prev
    Next
    INDEX
    Explanations

    references to modifications or modules in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     ivelany
    -1.03
     HasFactory
    -1.02
    FieldBuilder
    -0.95
    esez
    -0.95
    Rhestr
    -0.94
    DockStyle
    -0.94
    findpost
    -0.92
     Houſe
    -0.90
    rawDesc
    -0.89
     nakalista
    -0.86
    POSITIVE LOGITS
    mod
    3.40
     mod
    3.38
     Mod
    3.30
    Mod
    3.21
    MOD
    2.63
     MOD
    2.58
     mods
    2.58
    Mods
    2.31
    mods
    2.29
     Mods
    2.25
    Activations Density 0.064%

    No Known Activations