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. 20-GEMMASCOPE-RES-131K
    6. 40747
    Prev
    Next
    INDEX
    Explanations

    details about crowded public spaces or situations

    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_20/width_131k/average_l0_114
    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
     laikā
    -0.44
     Ganzen
    -0.34
     senare
    -0.34
     stället
    -0.32
     sprawd
    -0.32
     ervan
    -0.32
     viață
    -0.32
     nicio
    -0.31
     nigdy
    -0.31
     conmigo
    -0.31
    POSITIVE LOGITS
    ########.
    0.70
    parency
    0.61
     $_-
    0.59
     annoying
    0.59
    ſicht
    0.59
    ſſung
    0.59
    <unused52>
    0.58
    <unused74>
    0.58
    <unused41>
    0.58
    <unused23>
    0.58
    Activations Density 0.041%

    No Known Activations