© 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. 24-GEMMASCOPE-RES-16K
    11. 11139
    Prev
    Next
    INDEX
    Explanations

    texts that express the idea of personal responsibility or ownership of content

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

    after articles (the, a) or possessive pronouns (your)

    np_acts-logits-general · gemini-2.0-flash

    purpose, site, path, help, mail, track, nav

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fordítás
    -0.22
    تم
    -0.19
    ENOMEM
    -0.18
    plaatst
    -0.17
    Vh
    -0.17
    Források
    -0.16
    ر
    -0.16
     السابق
    -0.15
    surfaces
    -0.15
    よ
    -0.15
    POSITIVE LOGITS
     WHITE
    0.60
     SUPER
    0.60
     BLACK
    0.60
     BEST
    0.59
     NEW
    0.59
     OVER
    0.58
     GOOD
    0.57
     LAST
    0.57
     MAJOR
    0.57
     BACK
    0.56
    Activations Density 25.605%

    No Known Activations