© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13913
    Prev
    Next
    INDEX
    Explanations

    negative descriptors associated with criminal behavior or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RenderAtEndOf
    -0.43
     ujednoznacz
    -0.34
    
    -0.34
     interesados
    -0.34
     Verhält
    -0.34
     enfans
    -0.32
     Betrieb
    -0.32
     suivants
    -0.32
     debido
    -0.31
     Interested
    -0.31
    POSITIVE LOGITS
     billions
    0.65
    ViewFeatures
    0.65
    IUrlHelper
    0.64
     AttributeSet
    0.64
    BeginContext
    0.63
    脚注の使い方
    0.62
     виправивши
    0.57
    UnknownFieldSet
    0.56
     scandals
    0.56
    
    0.56
    Activations Density 0.414%

    No Known Activations