© 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. 20-GEMMASCOPE-RES-16K
    11. 8008
    Prev
    Next
    INDEX
    Explanations

    the start of a new section within the document

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

    Followed by a question mark

    np_acts-logits-general · gemini-2.0-flash

    Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++
    -1.23
     }}$}
    -1.18
    >\<^
    -1.09
    \<^
    -1.09
    )");
    -1.07
    }.
    -1.07
    ".
    -1.06
    )";
    -1.05
     $_"
    -1.03
    $.
    -1.03
    POSITIVE LOGITS
    <eos>
    0.94
    https
    0.94
    ↵↵
    0.94
    ↵
    0.86
    http
    0.78
    I
    0.74
    "
    0.72
    ↵↵↵↵
    0.71
        
    0.70
    “
    0.70
    Activations Density 0.123%

    No Known Activations