© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 4148
    Prev
    Next
    INDEX
    Explanations

    programming terms and syntax related to code structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    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>
    -0.79
    </s>
    -0.73
    ")]
    -0.71
    </th>
    -0.70
    "]);
    -0.70
    "])
    -0.69
    "]),
    -0.69
    "]));
    -0.69
    ."]
    -0.69
    ")]
    -0.68
    POSITIVE LOGITS
     argint
    0.37
    ométrie
    0.37
    kháu
    0.36
     MaterialApp
    0.35
     uLocal
    0.34
    putstr
    0.34
    astă
    0.33
    Sklici
    0.33
     contemplates
    0.33
     становника
    0.32
    Activations Density 0.963%

    No Known Activations