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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 8656
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and important figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Titles of political figures

    np_acts-logits-general · gemini-2.0-flash

    political leader titles followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.83
     تانيه
    -0.77
     fubject
    -0.69
     iſt
    -0.69
    ंदीखरीदारी
    -0.69
     للمعارف
    -0.68
     purpoſe
    -0.67
     myſelf
    -0.67
     RSSSF
    -0.67
    ſelves
    -0.66
    POSITIVE LOGITS
    InjectAttribute
    0.47
     Incar
    0.46
     Jinping
    0.44
     His
    0.43
    thâu
    0.42
     besos
    0.41
     Recep
    0.41
     cuello
    0.40
     bless
    0.40
     Hage
    0.40
    Activations Density 0.174%

    No Known Activations