© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4341
    Prev
    Next
    INDEX
    Explanations

    technical details related to software applications and their updates

    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
    ”).
    -0.88
    <eos>
    -0.85
    ”.
    -0.70
    ”。
    -0.69
    ”]
    -0.68
    "}>
    -0.68
     }.
    -0.67
    "].
    -0.65
     "").
    -0.63
    ]").
    -0.63
    POSITIVE LOGITS
    </td>
    2.80
    </th>
    1.51
    </h2>
    1.10
    </blockquote>
    1.09
    </h3>
    0.98
    </h1>
    0.94
    </h5>
    0.94
    </i>
    0.88
    ',
    0.81
    </b>
    0.75
    Activations Density 0.053%

    No Known Activations