© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2642
    Prev
    Next
    INDEX
    Explanations

    actions or verbs related to movement and processes

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

    a sequence of events

    np_acts-logits-general · gemini-2.0-flash

    events thereafter

    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
     and
    -0.81
    DebuggerNonUser
    -0.66
     snippetHide
    -0.65
     disponibilités
    -0.65
    Personendaten
    -0.63
    TagMode
    -0.61
    jsdelivr
    -0.60
    featureID
    -0.60
     surla
    -0.60
    */),
    -0.60
    POSITIVE LOGITS
     accordingly
    0.69
     vervolgens
    0.64
     thereafter
    0.60
    usnya
    0.58
     thereunder
    0.55
     afterwards
    0.55
     therefrom
    0.55
     Afterwards
    0.54
    Then
    0.54
     así
    0.53
    Activations Density 0.338%

    No Known Activations