© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7490
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the formation or creation of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the verb "establish" or "establishing" used to indicate proof, creation, or founding of something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.56
    migrationBuilder
    -0.54
    Välislingid
    -0.54
     IFTT
    -0.50
     estekak
    -0.50
    ⓧ
    -0.47
    ########.
    -0.47
    Tembelea
    -0.47
     autorytatywna
    -0.47
     Италијани
    -0.47
    POSITIVE LOGITS
     établie
    0.81
     ESTABL
    0.74
     established
    0.74
     Establish
    0.73
     Establishing
    0.73
    established
    0.72
    Establish
    0.71
     establish
    0.71
     establishes
    0.70
    Establishing
    0.69
    Activations Density 0.098%

    No Known Activations