© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8879
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or whitespace characters in the 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
    <h5>
    -1.37
     CommonModule
    -0.81
    AndEndTag
    -0.77
    例句
    -0.75
    tieth
    -0.73
    uple
    -0.73
     Mahan
    -0.68
    {%
    -0.68
    </h5>
    -0.67
    ↵↵↵↵
    -0.67
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.13
    </h6>
    1.10
    ↵↵↵↵↵
    1.09
    ↵↵↵↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵
    0.94
    ↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    Activations Density 0.093%

    No Known Activations