© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5458
    Prev
    Next
    INDEX
    Explanations

    specific programming-related commands and constructs within a codebase

    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
    AutoScaleMode
    -1.54
    GEBURTSDATUM
    -1.41
     nahilalakip
    -1.33
    adaptiveStyles
    -1.32
    ⓧ
    -1.29
    Rüyada
    -1.29
    NameInMap
    -1.27
     Roskov
    -1.25
    MigrationBuilder
    -1.24
    :✨
    -1.21
    POSITIVE LOGITS
     ơn
    0.66
    ertale
    0.61
    endforeach
    0.60
    initState
    0.58
    TacToe
    0.57
    ==========
    0.57
     userSchema
    0.56
    — 
    0.55
    soever
    0.55
    Schriften
    0.54
    Activations Density 4.933%

    No Known Activations