© 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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9828
    Prev
    Next
    INDEX
    Explanations

    references to methods and figures presented in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.72
    Rohy
    -0.70
    enderror
    -0.68
    LookAnd
    -0.67
    Hozzáférés
    -0.66
    IUrlHelper
    -0.64
    IsContent
    -0.62
    Bioaccumulative
    -0.62
    AlterField
    -0.60
    }))
    
    -0.60
    POSITIVE LOGITS
     mentioned
    1.06
     described
    0.95
     listed
    0.94
     AssemblyCulture
    0.90
     below
    0.87
     shown
    0.87
     pictured
    0.87
    ictured
    0.87
     stated
    0.86
     depicted
    0.85
    Activations Density 0.587%

    No Known Activations