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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3209
    Prev
    Next
    INDEX
    Explanations

    numerous instances of the word "the" and variations of article usage in the text

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

    Follows "the"

    np_acts-logits-general · gemini-2.0-flash

    the following specific 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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ſeveral
    -0.64
     محفوظة
    -0.60
     purpoſe
    -0.59
     ilustracja
    -0.59
     ſtate
    -0.59
     Reſ
    -0.57
     combatt
    -0.54
     adquis
    -0.54
    -------
    -0.53
     ſta
    -0.53
    POSITIVE LOGITS
     ​​
    0.38
     otomatig
    0.37
     Италијани
    0.36
    NOPQRST
    0.35
    adaptiveStyles
    0.33
    Condol
    0.33
     løpet
    0.32
     
    
    0.31
    ESTON
    0.31
     GetEnumerator
    0.31
    Activations Density 0.920%

    No Known Activations