© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5220
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific names and references within legal and political contexts

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

    Following "the," "week," "tension," "conflict," or "troubles"

    np_acts-logits-general · gemini-2.0-flash

    political conflicts and tensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krakowie
    -0.38
     relatively
    -0.37
     pulito
    -0.36
    requently
    -0.36
    意外と
    -0.34
    requent
    -0.34
     crescere
    -0.33
     szy
    -0.33
     pretty
    -0.33
    EMPT
    -0.33
    POSITIVE LOGITS
     nakalista
    0.84
    principalColumn
    0.81
    RegressionTest
    0.79
    IUrlHelper
    0.69
    InitVars
    0.67
    CloseOperation
    0.65
    MemoryWarning
    0.64
    reportWebVitals
    0.59
     NSCoder
    0.58
    хьтан
    0.57
    Activations Density 0.632%

    No Known Activations