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. 16-GEMMASCOPE-RES-16K
    6. 5115
    Prev
    Next
    INDEX
    Explanations

    references to family gatherings and shared meals

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

    Preceding words/symbols before/after parentheses

    np_acts-logits-general · gemini-2.0-flash

    hanging out together, or interviewed

    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
    .
    -0.41
    logii
    -0.38
     des
    -0.36
     (
    -0.35
     rep
    -0.35
    x
    -0.35
    :
    -0.34
     wanted
    -0.34
     
    -0.34
    um
    -0.34
    POSITIVE LOGITS
     OFDb
    1.05
    __":
    
    1.01
    __':
    
    0.99
     leisure
    0.99
     pleaſure
    0.97
     enjoyment
    0.97
     evenings
    0.90
     Roskov
    0.90
    gether
    0.89
     leisurely
    0.89
    Activations Density 0.164%

    No Known Activations