© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3804
    Prev
    Next
    INDEX
    Explanations

    packages and class declarations in a programming context.

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

    Java import statements related to repositories or frameworks.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    package and import statements in Java/Kotlin code, particularly those related to application frameworks and libraries.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Code or technical terms

    np_acts-logits-general · gemini-2.0-flash

    technical code delimiters

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    "]),
    -0.91
    ']}
    -0.87
    "]);
    
    -0.85
    ')],
    -0.84
    ']")
    -0.84
    ']);
    
    -0.83
    ()],
    -0.83
    ']],
    -0.83
    ())),
    -0.80
    "],
    
    -0.80
    POSITIVE LOGITS
    .
    0.96
    CodeAttribute
    0.63
     للمعارف
    0.56
    ⓘ
    0.56
    mybatisplus
    0.56
    AndEndTag
    0.50
    DropTable
    0.50
    ưỡi
    0.48
    gpl
    0.48
    Erreferentziak
    0.47
    Activations Density 0.079%

    No Known Activations