© 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. 1-GEMMASCOPE-RES-16K
    11. 3151
    Prev
    Next
    INDEX
    Explanations

    repeated references to the name Lincoln and terms associated with colors, especially shades of purple

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eindruck
    -0.37
    scriptcase
    -0.35
     montant
    -0.35
    romolecules
    -0.35
    mtrl
    -0.35
    ímp
    -0.35
     Verhält
    -0.35
     curé
    -0.34
    bleau
    -0.34
     Leute
    -0.34
    POSITIVE LOGITS
     Angela
    0.79
    awaiter
    0.77
    Angela
    0.77
    angular
    0.72
     生命周期
    0.72
    
    0.69
    vue
    0.66
     OnInit
    0.63
     Ange
    0.62
    ModelSerializer
    0.61
    Activations Density 0.234%

    No Known Activations