© 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. 18-GEMMASCOPE-RES-16K
    11. 4484
    Prev
    Next
    INDEX
    Explanations

    sections of code that involve data insertion or manipulation in various programming contexts

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

    Text before the word "here"

    np_acts-logits-general · gemini-2.0-flash

    keyword followed by here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.70
     dAtA
    -0.70
    DockStyle
    -0.64
    IsMutable
    -0.63
    NameInMap
    -0.60
    UnknownFields
    -0.58
     שוליים
    -0.55
    PyExc
    -0.55
    曖昧さ回避
    -0.55
     FormsModule
    -0.54
    POSITIVE LOGITS
     here
    2.17
    here
    1.75
     Here
    1.62
     aquí
    1.61
    Here
    1.55
     aqui
    1.50
     HERE
    1.50
     ici
    1.43
     здесь
    1.43
    HERE
    1.39
    Activations Density 0.611%

    No Known Activations