© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    references to panels or discussions involving multiple participants

    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
    */),
    -0.66
     sortie
    -0.59
     Coimbra
    -0.58
     Zuma
    -0.55
     فريبيس
    -0.55
     Sociale
    -0.55
     carats
    -0.54
     propOrder
    -0.54
    سكرية
    -0.54
    UseVisualStyle
    -0.54
    POSITIVE LOGITS
     panel
    4.03
     Panel
    3.82
    panel
    3.78
    Panel
    3.60
     panels
    3.58
     PANEL
    3.39
     Panels
    3.26
    PANEL
    3.11
    panels
    3.08
    Panels
    2.89
    Activations Density 0.039%

    No Known Activations