© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6872
    Prev
    Next
    INDEX
    Explanations

    sentences that express claims or statements, especially those starting with "that."

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

    grammatical constructions involving the word "that" in complex sentences.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     ब्रेकडाउन
    -0.52
     spørgsmål
    -0.49
     questions
    -0.49
    いしい
    -0.48
     nzuri
    -0.47
     Einfluß
    -0.47
    ieR
    -0.45
     unprecedented
    -0.45
    autant
    -0.45
     Geset
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
     bahawa
    0.46
     bahwa
    0.46
    Personendaten
    0.46
     rằng
    0.45
     that
    0.43
    ]")]
    0.43
     kwamba
    0.40
     ότι
    0.39
     dass
    0.38
    Activations Density 0.510%

    No Known Activations