© 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. 6107
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    Punctuation, conjunctions, and discourse markers

    np_acts-logits-general · gemini-2.0-flash

    probable that

    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
    __':
    
    -0.79
    AxisAlignment
    -0.77
     />';
    -0.76
     esche
    -0.75
    __":
    
    -0.75
    — 
    -0.73
     leveraging
    -0.72
    Folks
    -0.68
    ;-)
    -0.67
    %);
    -0.67
    POSITIVE LOGITS
     idk
    1.09
     Idk
    0.96
    Idk
    0.90
    idk
    0.88
     ;-;
    0.83
     ngl
    0.71
     irl
    0.71
    Ikr
    0.71
     kinda
    0.67
     tryna
    0.67
    Activations Density 0.423%

    No Known Activations