© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14287
    Prev
    Next
    INDEX
    Explanations

    past tense verb forms indicating actions performed in scientific processes or experiments

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

    Passive voice form of verbs

    np_acts-logits-general · gemini-2.0-flash

    passive voice past participles

    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
     geçen
    -0.51
    common
    -0.50
     bacio
    -0.48
     happening
    -0.47
     béné
    -0.46
     mencetak
    -0.46
     automatico
    -0.45
    سي
    -0.45
    A
    -0.45
     compréhen
    -0.44
    POSITIVE LOGITS
    AddHtmlAttribute
    0.80
     bezeichneter
    0.76
    parsedMessage
    0.75
     Wikimedijinoj
    0.75
    UnsafeEnabled
    0.72
     CreateTagHelper
    0.72
    QMetaType
    0.71
    initComponents
    0.71
    MethodManager
    0.70
     Infórmanos
    0.70
    Activations Density 0.826%

    No Known Activations