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. 10422
    Prev
    Next
    INDEX
    Explanations

    references to historical wars and their conditions

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

    Appearing before a type of war

    np_acts-logits-general · gemini-2.0-flash

    specific wars and conflicts

    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
     CURIAM
    -0.71
     المعيارى
    -0.71
     parseFrom
    -0.71
    Cyfeiriadau
    -0.69
    CppMethod
    -0.66
    новништво
    -0.63
     AttributeSet
    -0.62
    økt
    -0.61
    PositiveButton
    -0.61
     pleaſure
    -0.61
    POSITIVE LOGITS
     war
    0.84
     War
    0.75
     wars
    0.72
     conflict
    0.71
     civil
    0.62
     conflicts
    0.62
     Civil
    0.59
     guerra
    0.59
     conflicto
    0.58
    conflict
    0.57
    Activations Density 0.233%

    No Known Activations