© 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. 5-GEMMASCOPE-RES-16K
    6. 13864
    Prev
    Next
    INDEX
    Explanations

    terms related to limits and thresholds in quantitative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Heh
    -0.53
     UnityEngine
    -0.51
     entstehen
    -0.51
    ⁣
    -0.50
     Si
    -0.49
    ulkan
    -0.48
     ích
    -0.48
     bedo
    -0.47
    october
    -0.46
    nolia
    -0.46
    POSITIVE LOGITS
     exceed
    1.39
     exceeding
    1.37
     exceeds
    1.36
     exceeded
    1.20
     beyond
    1.12
     BEYOND
    1.08
     dépasse
    1.05
    beyond
    1.04
     Beyond
    0.98
    Exceeded
    0.93
    Activations Density 0.325%

    No Known Activations