© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7861
    Prev
    Next
    INDEX
    Explanations

    references to low-cost or low-income situations

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

    "low" and low cost

    np_acts-logits-general · gemini-2.0-flash

    low cost, budget, income, oil low cost, budget, income, oil, back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     StyleSheet
    -0.67
     وتسجيلات
    -0.60
    forName
    -0.59
    ]='\
    -0.55
     inoxydable
    -0.55
    ultati
    -0.55
     AssemblyCompany
    -0.54
     graphiques
    -0.53
     supérieurs
    -0.51
     économ
    -0.51
    POSITIVE LOGITS
    down
    0.75
    rider
    0.74
    cost
    0.70
     (<
    0.68
    key
    0.67
     cost
    0.67
     hanging
    0.66
    eſt
    0.66
    theless
    0.64
    enterOuterAlt
    0.64
    Activations Density 0.150%

    No Known Activations