© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4271
    Prev
    Next
    INDEX
    Explanations

    references to commercial and office buildings, particularly their characteristics and specifications

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

    Followed by "ft" or "user"

    np_acts-logits-general · gemini-2.0-flash

    sq ft, purlins, user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ường
    -0.31
     fer
    -0.29
     Fer
    -0.29
    lodash
    -0.28
     pi
    -0.28
     пи
    -0.27
     ri
    -0.26
     fan
    -0.24
        
    -0.24
    ぐ
    -0.24
    POSITIVE LOGITS
    enablog
    0.68
    MLLoader
    0.68
     estekak
    0.68
    hyrchwyd
    0.65
    mpagne
    0.64
    ðsíða
    0.64
     estadounid
    0.64
     surla
    0.64
     Lightboxes
    0.63
     kasarigan
    0.63
    Activations Density 0.151%

    No Known Activations