© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7295
    Prev
    Next
    INDEX
    Explanations

    references to intelligence and intelligence-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.76
    fromnode
    -0.72
     AssemblyCulture
    -0.70
     ويكيپيديا
    -0.69
    ViewById
    -0.69
     feroit
    -0.68
     mauvaises
    -0.67
    antwoorde
    -0.66
     Ause
    -0.65
     économies
    -0.65
    POSITIVE LOGITS
     intelligence
    2.05
     Intelligence
    1.99
    intelligence
    1.77
    Intelligence
    1.68
     INTELL
    1.32
     intelligen
    1.28
     intel
    1.20
     Intelligen
    1.14
    intel
    1.10
     Intel
    1.09
    Activations Density 0.062%

    No Known Activations