© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or connectors, particularly variations of "in."

    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
     ―――――
    -1.50
     ་་
    -1.48
     Anſ
    -1.46
     ――――――――
    -1.28
     iſt
    -1.24
     itſelf
    -1.24
     Monfieur
    -1.23
    ſelf
    -1.21
     Theſe
    -1.13
     myſelf
    -1.12
    POSITIVE LOGITS
     en
    2.46
     EN
    1.19
     em
    1.08
     in
    1.04
     En
    0.97
    en
    0.96
     σε
    0.92
     on
    0.91
     в
    0.88
     at
    0.85
    Activations Density 0.024%

    No Known Activations