© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1663
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures

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

    keywords related to programming concepts and data structures in a coding context

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

    Objective-C types

    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
    ”.
    -0.50
    ">//
    -0.49
    :+:
    -0.49
    ?.
    -0.49
    }>;
    -0.48
    }.\
    -0.48
    ?\
    -0.47
     =
    
    -0.47
    }
    
    -0.47
    cookieParser
    -0.47
    POSITIVE LOGITS
     Efq
    0.61
    énario
    0.61
     ་་
    0.60
    mybatisplus
    0.58
     ―――――
    0.57
    \{\\
    0.57
    HttpFoundation
    0.56
     Paulista
    0.55
     prospec
    0.55
     doubtnut
    0.55
    Activations Density 0.017%

    No Known Activations