© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9083
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to newsletters and subscription information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.68
    tagHelperRunner
    -0.68
    ########.
    -0.58
     CreateTagHelper
    -0.58
    ValueStyle
    -0.56
    
    -0.50
    Rüyada
    -0.50
     MainAxisSize
    -0.50
    jspb
    -0.50
     Roskov
    -0.50
    POSITIVE LOGITS
    </b>
    1.34
    </strong>
    1.29
    </u>
    1.23
    </i>
    1.07
    </em>
    1.03
    </code>
    0.90
    </h3>
    0.76
    </h4>
    0.70
    </h2>
    0.69
    </sup>
    0.65
    Activations Density 2.798%

    No Known Activations