© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104747
    Prev
    Next
    INDEX
    Explanations

    HTML tags in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.94
     CreateTagHelper
    -0.92
     queſta
    -0.85
     juſ
    -0.84
     ſche
    -0.84
     ſta
    -0.84
     ſever
    -0.84
     pleaſure
    -0.83
     ſur
    -0.83
     BoxDecoration
    -0.82
    POSITIVE LOGITS
    </i>
    0.95
    </em>
    0.79
    </sup>
    0.63
    </sub>
    0.63
    </u>
    0.63
    </s>
    0.57
    </b>
    0.51
    .
    0.49
      
    0.47
     */
    0.47
    Activations Density 0.000%

    No Known Activations