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. 20-GEMMASCOPE-RES-16K
    6. 15519
    Prev
    Next
    INDEX
    Explanations

    phrases related to musical performances and events involving artists

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

    followed by infinitive "to" or verb

    np_acts-logits-general · gemini-2.0-flash

    appear, perform, participate, write, promote, star

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     kiệm
    -0.57
     notare
    -0.54
     remarquer
    -0.54
    ScopeManager
    -0.52
     Acquisition
    -0.52
     stratégies
    -0.52
     omnia
    -0.51
    عام
    -0.50
     useParams
    -0.49
     fidèles
    -0.49
    POSITIVE LOGITS
     participated
    0.79
     host
    0.76
     participate
    0.76
     guest
    0.76
    particip
    0.74
     performs
    0.71
     perform
    0.70
     participates
    0.69
     appearing
    0.68
     appear
    0.67
    Activations Density 0.212%

    No Known Activations