Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 993
    Prev
    Next
    INDEX
    Explanations

    references to footage and images used in media production

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

    visual media clips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    #+#
    -0.63
    reportWebVitals
    -0.62
    MigrationBuilder
    -0.61
     jspb
    -0.56
    Personendaten
    -0.54
    tagext
    -0.54
    الحياه
    -0.51
    Cyfarwyddwr
    -0.47
    WriteTagHelper
    -0.47
     Himo
    -0.47
    POSITIVE LOGITS
     collage
    0.54
     images
    0.51
     viejos
    0.46
     disparate
    0.44
    getImage
    0.44
     vintage
    0.43
    昔の
    0.43
     görüntüleri
    0.43
    utebol
    0.43
     clips
    0.43
    Activations Density 0.018%

    No Known Activations