© 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. 24-GEMMASCOPE-RES-16K
    11. 4731
    Prev
    Next
    INDEX
    Explanations

    instances of the word "de" and its variations

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

    After token "De" or "de"

    np_acts-logits-general · gemini-2.0-flash

    de followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.75
    /**
    -0.59
    StructEnd
    -0.59
    contentLoaded
    -0.59
     forward
    -0.55
    Demografie
    -0.54
     createState
    -0.54
     oprot
    -0.53
    UnsafeEnabled
    -0.53
    دانشنامهٔ
    -0.53
    POSITIVE LOGITS
     facto
    0.43
    商品説明
    0.43
    ValueStyle
    0.43
     للمعارف
    0.41
    udas
    0.41
     bedste
    0.40
    irdre
    0.40
    liber
    0.40
     graded
    0.39
     Beers
    0.39
    Activations Density 0.103%

    No Known Activations