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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23405
    Prev
    Next
    INDEX
    Explanations

    links to software download sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Abp
    -0.40
     ban
    -0.39
    над
    -0.38
     absl
    -0.37
    el
    -0.36
    Bruh
    -0.36
    annes
    -0.36
    s
    -0.36
     ab
    -0.35
     rely
    -0.35
    POSITIVE LOGITS
    photobucket
    4.78
    imageshack
    1.22
    twimg
    0.68
     billeder
    0.65
    ocities
    0.60
     AssemblyCompany
    0.60
     miniaturka
    0.59
    bootstrapcdn
    0.58
    timg
    0.57
    StoryboardSegue
    0.57
    Activations Density 0.000%

    No Known Activations