© 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. 1-GEMMASCOPE-RES-16K
    6. 9130
    Prev
    Next
    INDEX
    Explanations

    the presence of the substring "pe"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LIABLE
    -0.59
     Colón
    -0.52
     Norris
    -0.52
     Poliz
    -0.51
    urably
    -0.51
    centralwidget
    -0.50
     Bever
    -0.50
    บรร
    -0.49
     "..\..\..\
    -0.48
    derung
    -0.48
    POSITIVE LOGITS
    pe
    3.87
    PE
    3.04
    Pe
    2.99
     pe
    2.94
     Pe
    2.73
     PE
    2.69
    pee
    1.73
    peg
    1.69
    pei
    1.64
    пе
    1.57
    Activations Density 0.039%

    No Known Activations