© 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. 20-GEMMASCOPE-RES-16K
    6. 5907
    Prev
    Next
    INDEX
    Explanations

    assignment operators and variable declarations

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

    Code snippets using "=" or ","

    np_acts-logits-general · gemini-2.0-flash

    new padding

    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
    Altre
    -0.53
    IndentedString
    -0.50
     sõ
    -0.50
    AsUp
    -0.50
    Pautan
    -0.49
    LEncoder
    -0.49
     ImportError
    -0.49
    Voci
    -0.49
     كمان
    -0.47
    ksikon
    -0.47
    POSITIVE LOGITS
    ")));
    
    0.70
    ]));
    
    0.70
    )));
    
    0.63
    ')")
    0.63
     تضيفلها
    0.62
     surla
    0.62
     дописавши
    0.59
     new
    0.59
    )))),
    0.57
     }}"></
    0.55
    Activations Density 0.008%

    No Known Activations