© 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. 20-GEMMASCOPE-RES-65K
    6. 1411
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest recommendations or suggestions to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases that suggest recommendations or suggestions of additional items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    suggesting possibilities or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    )"),
    -0.47
    IMPORTED
    -0.45
    -",
    -0.44
    اده
    -0.44
    "]
    
    -0.44
    ()]
    
    -0.43
     ),
    
    -0.43
    dente
    -0.43
     aspek
    -0.43
     }
    
    -0.42
    POSITIVE LOGITS
     Baillargeon
    0.98
    ConstraintMaker
    0.97
    expandindo
    0.85
    LLocation
    0.83
     Roskov
    0.80
     disambiguazione
    0.79
    IntoConstraints
    0.77
    Personensuche
    0.77
     unknownFields
    0.75
    webElementXpaths
    0.74
    Activations Density 0.023%

    No Known Activations