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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5381
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to guidance and strategies for problem-solving or management tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.79
    BufferException
    -0.78
    GEBURTSDATUM
    -0.71
    enablog
    -0.60
    
    -0.60
     erſt
    -0.59
     imagui
    -0.58
    𓆱
    -0.57
     wiſſen
    -0.57
     zwiſchen
    -0.57
    POSITIVE LOGITS
     benefits
    0.40
     beneficial
    0.39
     improves
    0.37
     beneficios
    0.36
     benefit
    0.36
     gives
    0.34
     forbed
    0.33
     bermanfaat
    0.33
     enhances
    0.33
     helps
    0.33
    Activations Density 0.477%

    No Known Activations