© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104836
    Prev
    Next
    INDEX
    Explanations

    references to amino acids and their characteristics

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

    amino acid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Посилання
    -0.54
     profesión
    -0.52
     vocación
    -0.52
    BrowserModule
    -0.51
     deuda
    -0.49
     regulación
    -0.48
     kyse
    -0.48
    get
    -0.48
     przypadku
    -0.47
    jenigen
    -0.47
    POSITIVE LOGITS
     Amino
    0.87
    Amino
    0.84
     amino
    0.79
    amino
    0.72
    lamino
    0.69
     amin
    0.68
    amin
    0.59
     Amin
    0.59
    Amin
    0.57
     AAS
    0.53
    Activations Density 0.014%

    No Known Activations