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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intent or decision-making actions

    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
    expandindo
    -0.59
     }{@
    -0.58
    ⟬
    -0.55
    UnusedPrivate
    -0.55
    ）』
    -0.55
    Personensuche
    -0.54
    InputTagHelper
    -0.53
    djangoproject
    -0.53
     >::
    -0.52
    centralwidget
    -0.51
    POSITIVE LOGITS
     decided
    0.76
     besluit
    0.76
     decidió
    0.75
     décidé
    0.73
     Decision
    0.72
     Scip
    0.72
     decide
    0.71
     متعلقه
    0.71
     decidido
    0.71
     referenties
    0.71
    Activations Density 0.247%

    No Known Activations