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. 69345
    Prev
    Next
    INDEX
    Explanations

    references to space exploration and related themes

    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
     виправивши
    -0.47
    tanleria
    -0.43
    InputBorder
    -0.40
    Życiorys
    -0.40
    */),
    -0.39
    CLUDING
    -0.39
     rojos
    -0.39
     transfieras
    -0.37
    tulo
    -0.36
    ↠
    -0.36
    POSITIVE LOGITS
     Space
    0.79
    Space
    0.75
     aerospace
    0.71
     Aerospace
    0.71
     space
    0.71
     pleaſure
    0.68
     science
    0.65
    space
    0.65
    berspace
    0.63
     useAuth
    0.63
    Activations Density 0.006%

    No Known Activations