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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5799
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions between partners or collaborators

    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
     strani
    -0.44
    pgterms
    -0.39
    amarca
    -0.39
    SFD
    -0.39
    псо
    -0.39
     prejudicial
    -0.36
    scribers
    -0.36
    dictions
    -0.35
    Hob
    -0.35
    cshtml
    -0.35
    POSITIVE LOGITS
     partner
    0.93
    partner
    0.82
     parceria
    0.81
     partnership
    0.79
    partnership
    0.75
     PARTNER
    0.75
     partnered
    0.74
    Partner
    0.72
     Partner
    0.70
     partners
    0.69
    Activations Density 0.686%

    No Known Activations