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. 12382
    Prev
    Next
    INDEX
    Explanations

    terms related to deterioration and its consequences in a business context

    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
    
    -0.36
    kost
    -0.36
    komp
    -0.36
    Anhalt
    -0.35
    parable
    -0.35
     Walkover
    -0.34
    iosk
    -0.34
    Igles
    -0.33
    onAttach
    -0.33
     remnant
    -0.32
    POSITIVE LOGITS
     feedback
    0.64
     Feedback
    0.59
    selbst
    0.54
     FEEDBACK
    0.52
     self
    0.51
    feedback
    0.50
    Feedback
    0.49
     himself
    0.49
     siebie
    0.47
     feedbacks
    0.47
    Activations Density 0.723%

    No Known Activations