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. 24-GEMMASCOPE-RES-16K
    6. 12780
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excitement or celebration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding verbs

    np_acts-logits-general · gemini-2.0-flash

    celebratory emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.91
     odkazy
    -0.61
    )=-\
    -0.56
    ]=-
    -0.55
    MENAFN
    -0.55
    }=-\
    -0.51
    )=-
    -0.51
     متعلقه
    -0.51
    Fatal
    -0.51
    optString
    -0.50
    POSITIVE LOGITS
     rejoicing
    1.79
     jub
    1.78
     overjoyed
    1.75
     rejoice
    1.74
     rejoiced
    1.70
     celebratory
    1.69
     celebration
    1.68
     elated
    1.63
     celebrate
    1.63
     celebrating
    1.59
    Activations Density 0.262%

    No Known Activations