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. 2-GEMMASCOPE-RES-16K
    6. 1246
    Prev
    Next
    INDEX
    Explanations

    terms related to intelligence and intelligence agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    prüche
    -0.60
    WriteTagHelper
    -0.57
     TROP
    -0.49
    seud
    -0.49
    WindowConstants
    -0.48
    sidemargin
    -0.48
     Bout
    -0.48
    descriptor
    -0.48
     Fest
    -0.47
    LayoutPanel
    -0.47
    POSITIVE LOGITS
     intelligence
    3.56
     Intelligence
    3.30
    intelligence
    3.06
    Intelligence
    3.00
     INTELL
    2.54
     intelligen
    2.26
     inteligencia
    2.18
     intel
    2.13
     Intelligen
    2.11
     inteligen
    1.94
    Activations Density 0.053%

    No Known Activations