© 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. 105559
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistical results

    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
    ंदीखरीदारी
    -0.88
     مرئيه
    -0.85
    \{\\
    -0.84
     unknownFields
    -0.82
    ſſung
    -0.81
    
    -0.81
     $_=
    -0.80
    __':
    -0.78
     deſſen
    -0.78
    <unused43>
    -0.78
    POSITIVE LOGITS
    1
    0.29
     (
    0.28
     metu
    0.28
     /
    0.27
    4
    0.26
    2
    0.26
    3
    0.25
    ,
    0.25
     implements
    0.25
            
    0.24
    Activations Density 0.178%

    No Known Activations