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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 1926
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or positive sentiment in relation to events or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kadang
    -0.65
     sometimes
    -0.62
     soms
    -0.60
     parfois
    -0.59
     Sometimes
    -0.58
     bazen
    -0.58
    sometimes
    -0.57
     иногда
    -0.54
    cobra
    -0.54
     manchmal
    -0.54
    POSITIVE LOGITS
    Excited
    0.98
     excited
    0.97
     Excited
    0.93
     thrilled
    0.92
    Joining
    0.88
     delighted
    0.86
     joining
    0.82
     Joining
    0.77
    SequentialGroup
    0.75
     joins
    0.75
    Activations Density 0.104%

    No Known Activations