© 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. 105564
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate relationships or additions between ideas

    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
     GenerationType
    -0.46
    transQ
    -0.44
     ProtoMessage
    -0.42
     通販
    -0.41
    richTextPanel
    -0.41
     MessageBoxIcon
    -0.40
    zii
    -0.40
    
    -0.38
     emplace
    -0.37
    ❹
    -0.37
    POSITIVE LOGITS
    '][$
    0.44
    muerzo
    0.44
     Schluß
    0.41
     étrangères
    0.41
     kaldı
    0.40
     antworte
    0.40
     OMITBAD
    0.40
     Greenwood
    0.38
     hängen
    0.38
    iodía
    0.38
    Activations Density 0.018%

    No Known Activations