© 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-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 535
    Prev
    Next
    INDEX
    Explanations

    references to statistical or mathematical methods and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.90
    "}>
    -0.79
    <?
    -0.77
    "});
    -0.75
    )".
    -0.74
    )».
    -0.72
    '".
    -0.70
    <eos>
    -0.69
    }".
    -0.69
    )}.
    -0.69
    POSITIVE LOGITS
     &
    1.60
    </h2>
    1.45
    </strong>
    1.39
    </td>
    1.10
    </th>
    1.04
    ,&
    1.02
    &
    0.93
     \&
    0.89
    </blockquote>
    0.87
    :&
    0.86
    Activations Density 0.098%

    No Known Activations