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. 12-GEMMASCOPE-RES-16K
    6. 12716
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical interactions and forces in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.75
     verſch
    -0.68
     Signalez
    -0.67
    
    -0.65
     Dieſe
    -0.64
     fashiola
    -0.63
    <unused43>
    -0.62
     zwiſchen
    -0.62
    <unused32>
    -0.61
    <unused76>
    -0.61
    POSITIVE LOGITS
     gravity
    0.36
     effect
    0.34
    Controllo
    0.33
    اطر
    0.33
     kesan
    0.31
     gravitational
    0.30
     Effekt
    0.28
    richTextPanel
    0.28
     radiation
    0.28
     prejudice
    0.27
    Activations Density 2.416%

    No Known Activations