© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2100
    Prev
    Next
    INDEX
    Explanations

    terms related to records and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invas
    -0.35
     iVar
    -0.35
     Alexander
    -0.35
     beverages
    -0.34
     Braid
    -0.34
     inven
    -0.33
     substitute
    -0.32
     mira
    -0.32
     reconstruction
    -0.31
    iVar
    -0.31
    POSITIVE LOGITS
     rec
    1.33
    rec
    1.32
     Rec
    1.30
     RECT
    1.22
    Rec
    1.20
     Rect
    1.16
    Rect
    1.16
    rect
    1.10
    RECT
    1.10
     rect
    1.09
    Activations Density 0.352%

    No Known Activations