© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8838
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web development and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     mães
    -0.51
     esferas
    -0.48
     directiva
    -0.48
     alça
    -0.47
    はじめに
    -0.47
     colonias
    -0.47
    határoz
    -0.45
     proyección
    -0.43
     tirantes
    -0.43
    fieras
    -0.43
    POSITIVE LOGITS
     HTML
    1.52
     HTTP
    1.47
     JavaScript
    1.43
     SQL
    1.42
     MySQL
    1.33
     MATLAB
    1.33
     UNIX
    1.32
     JSON
    1.31
     XML
    1.31
     PHP
    1.27
    Activations Density 0.670%

    No Known Activations