© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3709
    Prev
    Next
    INDEX
    Explanations

    various expressions of acknowledgment and commentary in conversational context

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

    Signals additional, related information

    np_acts-logits-general · gemini-2.0-flash

    introducing additional points

    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
    ']],
    -0.72
     endregion
    -0.66
    ']):
    -0.63
     */;
    -0.61
     />";
    -0.59
     }],
    -0.59
    etheless
    -0.59
    ennom
    -0.58
    ')):
    -0.58
     />';
    -0.57
    POSITIVE LOGITS
     forgot
    0.99
     BTW
    0.96
    顺便
    0.95
     btw
    0.95
     note
    0.94
     remember
    0.91
     FYI
    0.88
    BTW
    0.85
     speaking
    0.84
    FYI
    0.83
    Activations Density 0.170%

    No Known Activations