© 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. 4-GEMMASCOPE-RES-16K
    11. 9760
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "hidden" or "latent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -1.01
    UserScript
    -0.96
    isSuccessful
    -0.82
    SupportActionBar
    -0.81
     rendus
    -0.79
    principalColumn
    -0.78
    didSet
    -0.78
    setVerticalGroup
    -0.78
    AutoScale
    -0.77
    migrationBuilder
    -0.76
    POSITIVE LOGITS
     hidden
    2.28
     Hidden
    2.15
    hidden
    2.08
    Hidden
    2.03
    HIDDEN
    1.84
     hiding
    1.80
     hide
    1.70
     hid
    1.62
    hiding
    1.53
     Hiding
    1.53
    Activations Density 0.057%

    No Known Activations