© 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. 8960
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    typographic dashes (en/em dashes) used as separators in text, such as for asides, titles, or date ranges.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     doubtnut
    -0.89
     $\$
    -0.88
     lowa
    -0.84
     Majefty
    -0.84
     fhort
    -0.81
     ''
    -0.80
     neceff
    -0.79
     LoginComponent
    -0.79
     pngtree
    -0.78
     neceffary
    -0.77
    POSITIVE LOGITS
     –
    2.38
    –
    1.84
    ––
    1.72
    .–
    1.64
    ––––
    1.57
    )–
    1.57
    ,–
    1.45
     –,
    1.33
    €“
    1.29
     –>
    1.26
    Activations Density 0.223%

    No Known Activations