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. 21-GEMMASCOPE-RES-16K
    6. 14908
    Prev
    Next
    INDEX
    Explanations

    monetary values and currency symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    ViewFeatures
    -0.65
    ')}}
    -0.64
    ');?>
    -0.64
    SourceChecksum
    -0.64
    fillType
    -0.63
    '));
    
    -0.62
    Gön
    -0.62
    reactstrap
    -0.62
    ⓧ
    -0.61
    %}
    -0.61
    POSITIVE LOGITS
    1
    0.66
     (£
    0.63
    2
    0.59
    5
    0.57
    -$
    0.55
    /$
    0.55
    3
    0.54
    $$
    0.54
     (€
    0.54
    £
    0.54
    Activations Density 0.126%

    No Known Activations