© 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. 11-GEMMASCOPE-RES-16K
    11. 8477
    Prev
    Next
    INDEX
    Explanations

    introductory phrases or structures in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.45
    ✨:
    -0.44
    enumi
    -0.41
    thâu
    -0.41
    rogels
    -0.41
     arco
    -0.38
    eddable
    -0.38
     calculées
    -0.37
     mengal
    -0.37
    ViewGroup
    -0.36
    POSITIVE LOGITS
    Primero
    0.99
    First
    0.98
    Firstly
    0.97
     Firstly
    0.86
     First
    0.86
    первых
    0.85
     zuerst
    0.84
     FIRST
    0.82
    首先
    0.82
     primero
    0.81
    Activations Density 0.279%

    No Known Activations