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. 16-GEMMASCOPE-RES-16K
    6. 12801
    Prev
    Next
    INDEX
    Explanations

    themes related to connections and relationships among individuals and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.60
     مواليد
    -0.48
    écu
    -0.47
    UserScript
    -0.44
    -/**
    -0.44
    UnsafeEnabled
    -0.43
     Optionen
    -0.42
    stanze
    -0.41
     Guo
    -0.41
     option
    -0.40
    POSITIVE LOGITS
     связь
    0.66
     connect
    0.60
     connection
    0.59
     ارتباط
    0.59
     connects
    0.57
    connect
    0.56
     Connecting
    0.56
     engagement
    0.56
    Connect
    0.55
     closeness
    0.53
    Activations Density 0.216%

    No Known Activations