© 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. 2-GEMMASCOPE-RES-16K
    11. 7428
    Prev
    Next
    INDEX
    Explanations

    quoted strings and their delimiters

    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>
    -0.79
    </strong>
    -0.78
    <em>
    -0.78
     —
    -0.72
    <strong>
    -0.70
    <sup>
    -0.70
     •
    -0.65
     انتظ
    -0.65
    '=>$
    -0.64
     McCall
    -0.63
    POSITIVE LOGITS
    \"
    2.50
     \"
    2.22
    .\"
    1.78
    =\"
    1.77
    (\"
    1.62
    \",
    1.57
    \'
    1.49
     "\"
    1.39
    \":\"
    1.39
    \"\
    1.38
    Activations Density 0.344%

    No Known Activations