Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    numerical values and indicators of currency or financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.44
     Newswire
    -0.38
    erden
    -0.38
     cradle
    -0.38
    rąg
    -0.38
    IGENCE
    -0.38
    Cidade
    -0.37
    shafen
    -0.37
    lahraga
    -0.36
     rationally
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.64
     CreateTagHelper
    0.57
     HasFactory
    0.56
    jsxFileName
    0.53
     للمعارف
    0.52
    
    0.51
    OGND
    0.51
    Personensuche
    0.50
     ब्रेकडाउन
    0.49
    pushFollow
    0.49
    Activations Density 0.686%

    No Known Activations