© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    linguistically complex or convoluted expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.71
     فريبيس
    -0.56
    runApp
    -0.52
    ウンテン
    -0.51
    ITERIA
    -0.51
     candidates
    -0.51
     CanadaChoose
    -0.51
     Adjutant
    -0.50
     Alp
    -0.49
     makl
    -0.49
    POSITIVE LOGITS
    Obrázky
    0.71
     صوتيه
    0.70
    Personendaten
    0.68
    TestingModule
    0.63
    writeFieldEnd
    0.63
     AssemblyProduct
    0.63
    Tembelea
    0.61
    Diwedd
    0.59
     appunto
    0.58
    ResumeLayout
    0.58
    Activations Density 1.546%

    No Known Activations