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. 3-GEMMASCOPE-RES-16K
    6. 12325
    Prev
    Next
    INDEX
    Explanations

    instances of words or phrases related to 'il' (likely referring to a specific contraction or context-specific usage)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.72
    OGND
    -0.66
    zwa
    -0.66
    ChildScrollView
    -0.63
     integrated
    -0.60
     تضيفلها
    -0.60
    razi
    -0.59
    asche
    -0.59
     Lapp
    -0.58
    EMOS
    -0.57
    POSITIVE LOGITS
    il
    2.58
    IL
    2.25
    ils
    1.92
     IL
    1.64
    ILS
    1.48
    ile
    1.45
    ila
    1.44
    iled
    1.41
     il
    1.40
    ilen
    1.38
    Activations Density 0.197%

    No Known Activations