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

    Neuronpedia

    Jacobian LensNEW
    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. 14600
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy and contradictions in behavior or beliefs

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

    expressing surprise, disbelief, or negativity

    np_acts-logits-general · gemini-2.0-flash

    skepticism, surprise, emotional disbelief

    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
    ."));
    -0.99
    MemoryWarning
    -0.94
     protoimpl
    -0.94
    "]);
    -0.92
    }")
    -0.91
    ">'+
    -0.90
     Мексичка
    -0.88
    ]));
    -0.88
    ")));
    -0.88
    '},
    -0.87
    POSITIVE LOGITS
    ?!?!
    1.03
    ?!
    1.02
    ???
    0.97
    ?!?
    0.92
     smh
    0.92
    !?!
    0.88
    !?
    0.86
    ?????
    0.85
    ????
    0.85
     because
    0.83
    Activations Density 0.815%

    No Known Activations