© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13164
    Prev
    Next
    INDEX
    Explanations

    biochemical terminology and interactions related to amino acids and protein structures

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

    Amino acid sequences or residues

    np_acts-logits-general · gemini-2.0-flash

    amino acid sequences and residues

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ロス
    -0.35
     Canada
    -0.34
    System
    -0.33
     entertainment
    -0.32
     System
    -0.31
    ณฑ
    -0.31
    getSystem
    -0.30
     tents
    -0.30
     games
    -0.29
    CategoryId
    -0.29
    POSITIVE LOGITS
    Jeografia
    0.59
     يتيمه
    0.59
    omores
    0.55
     Савезне
    0.54
     مشين
    0.53
     residues
    0.52
    swick
    0.52
     nakalista
    0.51
    locked
    0.51
     Desain
    0.49
    Activations Density 1.425%

    No Known Activations