Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 113920
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "one" and its context in phrases

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

    one followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createDate
    -0.42
    lanta
    -0.40
     EconPapers
    -0.39
    CDA
    -0.38
    arrings
    -0.38
     getAddress
    -0.38
    ModelAttribute
    -0.37
    TypedDataSet
    -0.37
    AccessFile
    -0.37
     Cort
    -0.36
    POSITIVE LOGITS
     Recent
    0.49
    Recent
    0.48
    urtstag
    0.46
     RECENT
    0.46
     Rptr
    0.46
     recent
    0.45
    Rptr
    0.45
    +#+#
    0.44
    Биография
    0.43
     إحدى
    0.42
    Activations Density 0.085%

    No Known Activations