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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6033
    Prev
    Next
    INDEX
    Explanations

    the word "the" and its variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.71
    SourceChecksum
    -0.71
     OMITBAD
    -0.69
     estekak
    -0.66
     pinulongan
    -0.64
     يتيمه
    -0.63
    PropertyChanging
    -0.60
     חיצוניים
    -0.59
    tanleria
    -0.59
    sizeCache
    -0.58
    POSITIVE LOGITS
     Wirth
    0.36
    ,
    0.35
    Male
    0.35
     muhimu
    0.34
    ↵↵
    0.34
    utah
    0.34
    boer
    0.34
    pace
    0.34
     vader
    0.34
     tố
    0.33
    Activations Density 1.548%

    No Known Activations