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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16266
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and public health-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.74
    IsContent
    -0.72
     imóvel
    -0.65
     AMC
    -0.63
     STC
    -0.63
    AMC
    -0.63
    Marek
    -0.63
    șe
    -0.61
    ***********/
    -0.59
    versiti
    -0.59
    POSITIVE LOGITS
     vibration
    0.89
     vibr
    0.88
     vibrate
    0.85
     Vibr
    0.83
    NameInMap
    0.81
     vibrations
    0.79
     Yo
    0.79
    expandindo
    0.78
    yo
    0.78
    Yo
    0.77
    Activations Density 0.162%

    No Known Activations