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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6271
    Prev
    Next
    INDEX
    Explanations

    concepts related to the prevention and treatment of cardiovascular diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    EndInit
    -0.51
    +#+#
    -0.47
    ArgsConstructor
    -0.46
    ंदीखरीदारी
    -0.46
     sede
    -0.45
     Ber
    -0.45
    __(/*!
    -0.44
    BaseAdapter
    -0.44
     bit
    -0.44
    bit
    -0.44
    POSITIVE LOGITS
     costs
    0.69
     outcomes
    0.69
     efficiency
    0.67
     cost
    0.65
     uſed
    0.64
     betweenstory
    0.64
     performance
    0.63
     overuse
    0.63
    outcomes
    0.63
    Mejores
    0.62
    Activations Density 0.802%

    No Known Activations