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. 13886
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events, particularly involving responsibility for notable actions and events

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

    Followed by names

    np_acts-logits-general · gemini-2.0-flash

    famous people and leaders

    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
    XmlAccessType
    -0.52
    ]]=
    -0.45
     cilind
    -0.43
    érrez
    -0.43
    atrième
    -0.42
     suivant
    -0.41
    Silva
    -0.41
    diğimiz
    -0.41
     sekunder
    -0.41
     recommandons
    -0.41
    POSITIVE LOGITS
     Mahatma
    1.18
     Hitler
    1.11
     Napoleon
    1.02
     President
    1.02
     Adolf
    1.00
     Barack
    0.98
     JFK
    0.98
     Gandhi
    0.97
     FDR
    0.93
     Einstein
    0.93
    Activations Density 0.910%

    No Known Activations