© 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. 104567
    Prev
    Next
    INDEX
    Explanations

    prepositions and expressions of spatial relationships

    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
     capitales
    -0.46
    นำ
    -0.43
     asesinado
    -0.42
     combinación
    -0.41
    accesso
    -0.40
     inici
    -0.40
     ferons
    -0.40
     toallas
    -0.40
     inversiones
    -0.40
    MathML
    -0.40
    POSITIVE LOGITS
    IndentedString
    0.66
    脚注の使い方
    0.63
    WireFormatLite
    0.62
    󠁮
    0.62
     فريبيس
    0.62
    webElement
    0.58
    EDEFAULT
    0.58
     esternos
    0.57
     numberWith
    0.57
    Ʋ
    0.57
    Activations Density 0.034%

    No Known Activations