© 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. 17-GEMMASCOPE-RES-16K
    6. 85
    Prev
    Next
    INDEX
    Explanations

    statements about national status or conditions related to countries

    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
    writeFieldEnd
    -0.62
     Sicilian
    -0.59
    حوالہ
    -0.58
     GenerationType
    -0.58
    ViewImports
    -0.58
    unnitel
    -0.58
    原始内容存档于
    -0.58
    المكان
    -0.57
     Leopoldo
    -0.56
    sterious
    -0.56
    POSITIVE LOGITS
     hosting
    0.66
     adopting
    0.56
     ratified
    0.56
    rrggbb
    0.54
     страна
    0.51
     nation
    0.50
     ratify
    0.50
     adoptar
    0.48
     host
    0.48
     ranked
    0.48
    Activations Density 0.280%

    No Known Activations