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. 16-GEMMASCOPE-RES-16K
    6. 5173
    Prev
    Next
    INDEX
    Explanations

    information about individuals involved in the music and performance arts

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

    Festivals, news outlets, and awards

    np_acts-logits-general · gemini-2.0-flash

    jazz festivals and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.75
     kaynağından
    -0.73
     HasFactory
    -0.65
     defaultstate
    -0.64
    Personensuche
    -0.62
    Clik
    -0.60
    raszamy
    -0.59
    Portale
    -0.59
    farwyddwr
    -0.58
    AutoScaleMode
    -0.58
    POSITIVE LOGITS
    twice
    0.69
    successfully
    0.60
     twice
    0.55
    Successfully
    0.54
     national
    0.53
     successfully
    0.53
     nationally
    0.52
     Awarded
    0.51
     culminated
    0.48
    多次
    0.48
    Activations Density 0.206%

    No Known Activations