© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2248
    Prev
    Next
    INDEX
    Explanations

    specific identifiers, likely related to names, codes, or entities of interest

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

    Tokens after numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    utah domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.93
    OGND
    -0.88
     مشين
    -0.83
    帖最后由
    -0.82
     kasarigan
    -0.79
    ]")]
    -0.79
     Chwiliwch
    -0.77
     يتيمه
    -0.74
    rungsseite
    -0.73
     мәкал
    -0.71
    POSITIVE LOGITS
     pente
    0.30
    格兰
    0.29
    ValueError
    0.28
     INSEE
    0.28
    build
    0.26
    šno
    0.25
     agora
    0.25
    Now
    0.25
    ścia
    0.24
    ografija
    0.24
    Activations Density 0.193%

    No Known Activations