© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6326
    Prev
    Next
    INDEX
    Explanations

    phrases indicating medical assessments or suitability for work

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

    Punctuation marks and the word "which"

    np_acts-logits-general · gemini-2.0-flash

    lists of nouns after common words

    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
    )$}
    -0.84
    ]")]
    -0.83
    tvguidetime
    -0.80
    '}>
    -0.76
     ddelweddau
    -0.75
    parsedMessage
    -0.75
    IntoConstraints
    -0.74
    存于互联网档案馆
    -0.73
    DoubleQuotes
    -0.73
    !’
    -0.73
    POSITIVE LOGITS
     your
    1.12
     you
    1.06
    your
    0.94
     yourself
    0.90
    Your
    0.82
     Your
    0.80
     IIRC
    0.80
    you
    0.77
     youre
    0.71
     effectivement
    0.71
    Activations Density 0.796%

    No Known Activations