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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15138
    Prev
    Next
    INDEX
    Explanations

    phrases indicating persistence or ongoing action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.69
     propOrder
    -0.61
    ôtel
    -0.59
    DoubleQuotes
    -0.58
    ----</
    -0.56
    offsetof
    -0.55
    ร์
    -0.53
    False
    -0.53
    Cartney
    -0.52
    zegovina
    -0.52
    POSITIVE LOGITS
     trotzdem
    1.02
     still
    1.00
    Still
    1.00
     Still
    0.99
     Dennoch
    0.96
    still
    0.95
     Trotzdem
    0.91
     dennoch
    0.91
     nonetheless
    0.87
     comunque
    0.86
    Activations Density 0.217%

    No Known Activations