© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8765
    Prev
    Next
    INDEX
    Explanations

    contractions of the word "it" or possessive forms related to the first person

    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
    <bos>
    -1.67
     Мексичка
    -1.09
    Portale
    -1.06
    rungsseite
    -0.99
     ―――――
    -0.92
     Савезне
    -0.91
     Baillargeon
    -0.90
    
    -0.88
    +#+
    -0.87
    osoba
    -0.87
    POSITIVE LOGITS
     You
    0.73
     you
    0.65
    You
    0.65
     it
    0.63
    y
    0.61
     They
    0.60
     a
    0.60
     and
    0.58
    g
    0.58
    ak
    0.57
    Activations Density 0.171%

    No Known Activations