© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 96620
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "next"

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

    next in sequence or list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    BrowserModule
    -0.56
     Utilizamos
    -0.49
     Feldman
    -0.46
     companyId
    -0.45
     spreken
    -0.44
     almofada
    -0.44
     fileSize
    -0.42
     Driscoll
    -0.42
    elman
    -0.42
    iertamente
    -0.42
    POSITIVE LOGITS
     next
    1.22
    next
    1.20
     NEXT
    1.19
    Next
    1.19
     Next
    1.18
    getNext
    1.10
    NEXT
    1.09
    GetNext
    1.02
     getNext
    1.01
    setNext
    1.00
    Activations Density 0.021%

    No Known Activations