© 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. 18-GEMMASCOPE-RES-16K
    11. 8418
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mal" in various contexts, particularly related to identity and culture

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

    The token "Mal" and its variants

    np_acts-logits-general · gemini-2.0-flash

    words starting with Mal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.74
     Clermont
    -0.67
     pitié
    -0.65
     cæ
    -0.62
    RetentionPolicy
    -0.61
     Clic
    -0.61
     caoutchouc
    -0.61
     Italij
    -0.59
     FontWeight
    -0.59
     sumpay
    -0.59
    POSITIVE LOGITS
     Mal
    1.23
    Mal
    1.15
     MAL
    1.14
     mal
    1.05
    MAL
    0.96
    mal
    0.88
     Malt
    0.80
     Malone
    0.73
     Malle
    0.68
     Mald
    0.67
    Activations Density 0.102%

    No Known Activations