© 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. 15-GEMMASCOPE-RES-16K
    11. 4763
    Prev
    Next
    INDEX
    Explanations

    elements and structures in code or markup language, particularly related to data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCa
    -0.61
     Tanner
    -0.58
    Liens
    -0.57
    xmlns
    -0.57
    CURLOPT
    -0.56
    Giao
    -0.54
    strconv
    -0.52
     henvisninger
    -0.52
    Спољашње
    -0.52
     many
    -0.51
    POSITIVE LOGITS
     للاسماء
    0.89
    tabular
    0.85
    )";
    0.81
    ).]
    0.79
    RegressionTest
    0.79
    ]));
    0.79
    "];
    0.77
    .";
    0.76
    }")]
    0.76
    )");
    0.75
    Activations Density 0.003%

    No Known Activations