© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39707
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and contracts related to corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionMode
    -0.57
     AssemblyCulture
    -0.57
     initComponents
    -0.54
    ModelAdmin
    -0.52
    esgue
    -0.50
    🙂
    -0.49
    Handlung
    -0.48
    mapStateToProps
    -0.48
    webElementXpaths
    -0.48
     lisboa
    -0.47
    POSITIVE LOGITS
     allegedly
    0.65
     purported
    0.65
    enumi
    0.64
     henvisninger
    0.60
     supposedly
    0.57
    NameValuePair
    0.57
     ostensibly
    0.56
     inappropri
    0.55
    IFICA
    0.55
    ectady
    0.54
    Activations Density 0.106%

    No Known Activations