Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 7409
    Prev
    Next
    INDEX
    Explanations

    terms related to Bitcoin implementation and regulatory recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Numerade
    -0.63
    ReusableCell
    -0.60
    __":
    
    -0.59
     StringTokenizer
    -0.58
     utafitiHapana
    -0.56
     ModelExpression
    -0.56
    Према
    -0.55
    ']->
    -0.55
    >';
    
    -0.54
    mels
    -0.54
    POSITIVE LOGITS
     block
    0.96
     blocks
    0.93
     Block
    0.85
    Block
    0.84
    block
    0.84
    blocks
    0.81
     BLOCK
    0.81
     Blocks
    0.81
     mining
    0.79
    getBlock
    0.78
    Activations Density 0.112%

    No Known Activations