© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 557
    Prev
    Next
    INDEX
    Explanations

    instances of the word "se" and related conjugations or forms in various contexts

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

    the reflexive pronoun "se" and its related contexts

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

    reflexive verbs in romance languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     متعلقه
    -0.65
     باخ
    -0.60
    onReady
    -0.58
     Савезне
    -0.58
    windowFixed
    -0.56
    titleMargin
    -0.56
    Wonder
    -0.54
     Wonder
    -0.54
    self
    -0.53
    WillAppear
    -0.53
    POSITIVE LOGITS
    Datuak
    0.58
     हमें
    0.48
    tvguidetime
    0.48
     chevaux
    0.45
    wendigkeit
    0.45
     gevolg
    0.45
    effetto
    0.45
     efecto
    0.44
    blå
    0.43
    cydow
    0.42
    Activations Density 0.004%

    No Known Activations