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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 1097
    Prev
    Next
    INDEX
    Explanations

    references to civil rights and civil society issues

    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
    Tunisia
    -0.86
     Moscou
    -0.82
     sonore
    -0.82
     artistique
    -0.81
     Tunisia
    -0.77
     acorns
    -0.76
     Thessaloniki
    -0.76
    LEncoder
    -0.76
     binoculars
    -0.76
     itſelf
    -0.74
    POSITIVE LOGITS
     civil
    4.11
     Civil
    3.93
    Civil
    3.69
    civil
    3.56
     CIVIL
    3.34
     civile
    2.42
    CIV
    2.30
     civils
    2.18
     Civ
    2.08
     civiles
    2.07
    Activations Density 0.049%

    No Known Activations