© 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. 2-GEMMASCOPE-RES-16K
    6. 907
    Prev
    Next
    INDEX
    Explanations

    references to file-related commands and actions in a coding context

    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
    enterOuterAlt
    -1.00
    NameInMap
    -0.99
     SqlDbType
    -0.94
    
    -0.92
    Personensuche
    -0.92
    المناصب
    -0.88
    LookAnd
    -0.86
    Personendaten
    -0.84
    GEBURTSDATUM
    -0.83
    Tikang
    -0.83
    POSITIVE LOGITS
     américain
    0.59
     Sénat
    0.57
     f
    0.56
    raltar
    0.56
     Ganes
    0.53
     urmă
    0.53
     planète
    0.52
    drage
    0.51
    ljiv
    0.51
     carica
    0.50
    Activations Density 0.285%

    No Known Activations