© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1153
    Prev
    Next
    INDEX
    Explanations

    elements related to information privacy and data handling practices

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

    code errors or legal jargon

    np_acts-logits-general · gemini-2.0-flash

    personal information and websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ger
    -0.45
     j
    -0.45
    <0xE2>
    -0.43
     w
    -0.43
     p
    -0.43
     n
    -0.42
     ge
    -0.42
    ветить
    -0.42
    landet
    -0.41
     c
    -0.41
    POSITIVE LOGITS
     فريبيس
    1.24
    GEBURTSDATUM
    1.23
    VIAF
    1.19
    Geplaatst
    1.18
    contentLoaded
    1.15
    Personensuche
    1.15
     '\\;'
    1.10
     unknownFields
    1.08
    Rüyada
    1.07
     Normdatei
    1.06
    Activations Density 1.066%

    No Known Activations