© 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. 10-GEMMASCOPE-RES-16K
    6. 12171
    Prev
    Next
    INDEX
    Explanations

    references to hotels and accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.59
    tructive
    -0.50
     tumors
    -0.48
    RenderAtEndOf
    -0.48
     зиму
    -0.46
     {;
    -0.46
    JScrollPane
    -0.46
    圳
    -0.45
     Moines
    -0.45
    脚注の使い方
    -0.45
    POSITIVE LOGITS
     hotel
    1.50
     hotels
    1.39
     Hotel
    1.29
    hotel
    1.25
    Hotel
    1.20
     Hotels
    1.16
     HOTEL
    1.15
     motel
    1.12
    HOTEL
    1.09
    hotels
    1.09
    Activations Density 0.073%

    No Known Activations