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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5066
    Prev
    Next
    INDEX
    Explanations

    occurrences of bold formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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>
    -1.21
     
    -1.18
    </strong>
    -0.96
    ",@"
    -0.95
    """.
    -0.94
    """)
    -0.91
    ."""
    -0.88
     propOrder
    -0.88
     fl
    -0.87
    HomeAsUpEnabled
    -0.86
    POSITIVE LOGITS
    <b>
    1.86
    </b>
    1.74
    dfrac
    1.35
    </i>
    1.26
    <i>
    0.99
     ± 
    0.84
     + 
    0.81
     &#
    0.81
    ècie
    0.79
     \[
    0.75
    Activations Density 0.154%

    No Known Activations