Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3998
    Prev
    Next
    INDEX
    Explanations

    the term "wife" and its variations, indicating a focus on familial relationships

    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
    inalg
    -0.74
    مو
    -0.72
     Kenn
    -0.71
     appart
    -0.69
    Mov
    -0.67
     bước
    -0.67
    Kenn
    -0.67
    llon
    -0.65
    ttal
    -0.65
     hoàn
    -0.64
    POSITIVE LOGITS
     wives
    1.28
     wife
    1.27
    wife
    1.21
     WIFE
    1.19
    wives
    1.14
     Wife
    1.10
     Wives
    1.03
    Wife
    0.99
     smtplib
    0.90
    y
    0.87
    Activations Density 0.152%

    No Known Activations