© 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. 23-GEMMASCOPE-RES-16K
    11. 15139
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.75
    AddTagHelper
    -0.72
    JsonKey
    -0.69
    Parcelize
    -0.62
     autorytatywna
    -0.62
    actionMode
    -0.62
     calendriers
    -0.57
    WithIOException
    -0.57
     cherchés
    -0.57
     pinulongan
    -0.57
    POSITIVE LOGITS
     fence
    1.33
     fencing
    1.25
     fences
    1.23
     barriers
    1.17
     barrier
    1.13
    fence
    1.10
     Fence
    1.09
    Barriers
    1.02
     mesh
    0.99
     Barriers
    0.98
    Activations Density 0.213%

    No Known Activations