© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11438
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and descriptions related to constructors and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    ]")
    -1.16
    ”]
    -1.13
    ]")]
    -1.13
    ")]
    -1.10
    ")]
    -1.09
    \"]
    -1.08
    "]);
    -1.07
    ]);
    -1.04
    "));
    -1.02
    POSITIVE LOGITS
    </h3>
    2.67
    <h3>
    1.05
    </td>
    0.92
    </h5>
    0.91
    </h1>
    0.88
    </sub>
    0.80
    </h2>
    0.73
    </h4>
    0.68
     \\
    0.67
    </blockquote>
    0.66
    Activations Density 0.039%

    No Known Activations