© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9125
    Prev
    Next
    INDEX
    Explanations

    HTML tags, specifically for emphasis and bold formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -1.83
    </strong>
    -1.70
    <strong>
    -1.45
    <em>
    -1.41
     
    -1.28
    ",@"
    -1.19
     fl
    -1.09
    """
    -0.96
    """
    -0.95
    "<<
    -0.95
    POSITIVE LOGITS
    </b>
    2.60
    </i>
    2.16
    dfrac
    1.48
    <b>
    1.44
    <i>
    1.39
    ']").
    1.10
    َّ
    1.10
     ± 
    1.06
     + 
    1.05
      
    1.04
    Activations Density 0.064%

    No Known Activations