© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8086
    Prev
    Next
    INDEX
    Explanations

    specific references to pagan practices and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.60
     насељу
    -0.59
     Audiodateien
    -0.54
    IntoConstraints
    -0.48
    AndEndTag
    -0.47
    
    -0.46
     &___
    -0.46
    艋
    -0.44
     Normdatei
    -0.42
     quæ
    -0.41
    POSITIVE LOGITS
     pag
    0.77
    Pag
    0.65
     Pag
    0.63
    pag
    0.60
     cooling
    0.58
    Cooling
    0.58
     CreateTagHelper
    0.57
     chill
    0.57
     chilled
    0.57
     Cooling
    0.56
    Activations Density 1.202%

    No Known Activations