© 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. 18-GEMMASCOPE-RES-16K
    11. 15264
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with conversational back-and-forth dialogue, particularly questions and affirmations

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

    Punctuation and disfluencies in speech/text

    np_acts-logits-general · gemini-2.0-flash

    punctuation and sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.96
    +:+
    -0.91
    )”.
    -0.87
    anmoins
    -0.85
    RepeatedField
    -0.84
     للمعارف
    -0.83
    ۜ
    -0.83
    tagHelperRunner
    -0.82
     utafitiHapana
    -0.81
    кож
    -0.80
    POSITIVE LOGITS
    .
    0.62
    Yeah
    0.58
    ♪
    0.52
     Yeah
    0.52
     gonna
    0.51
     ♪
    0.49
     yeah
    0.49
    -
    0.46
    OK
    0.46
    '
    0.45
    Activations Density 0.097%

    No Known Activations