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. 18-GEMMASCOPE-RES-16K
    6. 833
    Prev
    Next
    INDEX
    Explanations

    quoted speech and expressions of opinions or feelings

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

    Text enclosed in quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.60
     فريبيس
    -0.57
     betweenstory
    -0.57
    sculpture
    -0.55
    yourself
    -0.54
     IBOutlet
    -0.53
    دانشنامهٔ
    -0.52
    opcional
    -0.52
    seater
    -0.51
     -
    -0.50
    POSITIVE LOGITS
     very
    0.77
    very
    0.74
    '):
    
    0.69
     ...
    
    0.68
     almost
    0.68
     absolutely
    0.67
    '>
    
    0.67
    }")
    
    0.67
     pretty
    0.67
    arith
    0.67
    Activations Density 0.138%

    No Known Activations