© 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. 16-GEMMASCOPE-RES-16K
    11. 8447
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and expressions that indicate dialogue or thought

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

    Followed by a comma or quote

    np_acts-logits-general · gemini-2.0-flash

    I was like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.79
    )__
    -0.60
     صوتيه
    -0.60
    itespace
    -0.59
    TagHelper
    -0.59
     "/")
    -0.59
    ihnachten
    -0.59
    ★★★★☆
    -0.59
    .。
    -0.57
    ]").
    -0.57
    POSITIVE LOGITS
     Hey
    0.71
    fjspx
    0.70
     давайте
    0.69
     Why
    0.67
     hey
    0.66
     Please
    0.64
     How
    0.63
     Let
    0.62
     please
    0.61
     veuillez
    0.60
    Activations Density 0.278%

    No Known Activations