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. 2-GEMMASCOPE-RES-16K
    6. 8511
    Prev
    Next
    INDEX
    Explanations

    references to "plug" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.51
     للاسماء
    -0.49
     ddelweddau
    -0.49
    AddTagHelper
    -0.47
     cherchés
    -0.46
     مواليد
    -0.46
    VYMaps
    -0.45
    bewerken
    -0.44
     betweenstory
    -0.44
     princí
    -0.44
    POSITIVE LOGITS
     Poison
    0.93
    Poison
    0.91
     plug
    0.88
     poison
    0.84
    poison
    0.81
     Toxic
    0.75
     Plug
    0.75
    plug
    0.75
    Plug
    0.71
     poisons
    0.71
    Activations Density 0.479%

    No Known Activations