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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 11372
    Prev
    Next
    INDEX
    Explanations

    instances of the word "its" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Könige
    -0.52
     pleaſure
    -0.52
    ReusableCell
    -0.50
     xPos
    -0.50
    Leer
    -0.49
     perſon
    -0.48
    parseColor
    -0.48
     getUsername
    -0.47
    Preference
    -0.47
    MediaStore
    -0.47
    POSITIVE LOGITS
     its
    1.13
    Its
    1.07
     Its
    1.01
    它
    0.89
    它的
    0.87
     Оно
    0.85
     它
    0.83
    its
    0.78
     ITS
    0.77
    及其
    0.74
    Activations Density 0.133%

    No Known Activations