© 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. 16-GEMMASCOPE-RES-16K
    6. 1952
    Prev
    Next
    INDEX
    Explanations

    elements related to chemical properties and processes in biological materials

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

    Tokens preceding certain nouns

    np_acts-logits-general · gemini-2.0-flash

    DNA fragments and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    czegó
    -0.44
     serem
    -0.38
     Defensa
    -0.38
    joy
    -0.36
     lieb
    -0.36
    发表于
    -0.36
     either
    -0.36
     olho
    -0.35
    في
    -0.35
     kic
    -0.35
    POSITIVE LOGITS
    Datuak
    0.86
     utafitiHapana
    0.78
    ########.
    0.74
     henceforth
    0.74
     thence
    0.73
    stateProvider
    0.71
     ISNI
    0.71
     resultant
    0.70
    こうして
    0.70
    AccessorTable
    0.70
    Activations Density 0.871%

    No Known Activations