© 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. 11563
    Prev
    Next
    INDEX
    Explanations

    references to "cha" or related terms, likely focusing on the concept of change or variety

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

    following "Cha"

    np_acts-logits-general · gemini-2.0-flash

    words starting with cha

    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
     cauſe
    -0.89
    CloseOperation
    -0.88
     itſelf
    -0.86
     pleaſure
    -0.81
     myſelf
    -0.81
    ]";
    -0.80
     purpoſe
    -0.80
     Efq
    -0.79
    ]));
    -0.78
    wiſe
    -0.76
    POSITIVE LOGITS
     cha
    0.83
     Cha
    0.82
    Cha
    0.80
    cha
    0.75
     CHAP
    0.57
     chameleon
    0.48
    y
    0.47
    CHA
    0.47
     Ча
    0.46
     CHAM
    0.45
    Activations Density 0.066%

    No Known Activations