© 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. 23-GEMMASCOPE-RES-16K
    11. 11878
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to technical specifications and performance metrics of materials and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.76
     dzięki
    -0.71
    хьтан
    -0.70
     grâce
    -0.65
     helps
    -0.65
     provides
    -0.65
    Demografía
    -0.65
     aiuta
    -0.64
     nhờ
    -0.64
    helps
    -0.62
    POSITIVE LOGITS
     causing
    1.63
    causing
    1.40
     resulting
    1.26
     causando
    1.25
     mengakibatkan
    1.24
    resulting
    1.21
    導致
    1.20
     menyebabkan
    1.20
    Worse
    1.19
     Worse
    1.19
    Activations Density 1.198%

    No Known Activations