© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8540
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "in" across various contexts

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

    prepositions that express being inside/within or occurring during something (primarily marking inclusion, location, or time).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the preposition "in" indicating participation or location

    oai_token-act-pair · deepseek-r1Triggered by @jyhe0408

    the preposition "in" when it introduces a context or domain where something occurs or exists.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Autoritní
    -0.45
     iron
    -0.36
    CategoryId
    -0.35
    тату
    -0.35
     Италијани
    -0.34
     Inspec
    -0.33
     artisans
    -0.33
    Iron
    -0.33
    gang
    -0.32
    omer
    -0.32
    POSITIVE LOGITS
    BufferException
    0.82
    MENAFN
    0.73
    writeField
    0.68
     arşivlendi
    0.66
    MemoryWarning
    0.65
    astify
    0.62
    \{\\
    0.62
    AndEndTag
    0.60
    存于互联网档案馆
    0.58
    MessageTagHelper
    0.57
    Activations Density 0.481%

    No Known Activations