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. 23-GEMMASCOPE-RES-131K
    6. 76
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and indigenous communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recibiendo
    -0.29
     ușor
    -0.28
     artificiales
    -0.27
    ņem
    -0.27
     remercie
    -0.27
     nicely
    -0.27
     légèrement
    -0.27
     mejorado
    -0.26
     sonriente
    -0.26
     helyzet
    -0.26
    POSITIVE LOGITS
     ब्रेकडाउन
    0.75
     remot
    0.75
     CreateTagHelper
    0.70
     ffilmiau
    0.69
     wilderness
    0.69
     inacces
    0.69
     Primitive
    0.68
     kaarangay
    0.68
     inaccessible
    0.68
    StoryboardSegue
    0.67
    Activations Density 0.030%

    No Known Activations