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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    expressions of indifference towards external opinions and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    υτό
    -0.51
    roned
    -0.48
     dou
    -0.48
     senso
    -0.47
     dú
    -0.45
    Doug
    -0.44
     trattano
    -0.43
    ′
    -0.43
    الصفحه
    -0.43
    kati
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.88
    MigrationBuilder
    0.86
    ьаж
    0.81
     whether
    0.79
    whether
    0.74
    afficheront
    0.73
     مرئيه
    0.73
     AssemblyCulture
    0.66
     AssemblyCompany
    0.66
     Offisielt
    0.66
    Activations Density 0.165%

    No Known Activations